20190305.md

ArXiv cs.CV --Tue, 5 Mar 2019

1.VideoFlow: A Flow-Based Generative Model for Video pdf

Generative models that can model and predict sequences of future events can, in principle, learn to capture complex real-world phenomena, such as physical interactions. In particular, learning predictive models of videos offers an especially appealing mechanism to enable a rich understanding of the physical world: videos of real-world interactions are plentiful and readily available, and a model that can predict future video frames can not only capture useful representations of the world, but can be useful in its own right, for problems such as model-based robotic control. However, a central challenge in video prediction is that the future is highly uncertain: a sequence of past observations of events can imply many possible futures. Although a number of recent works have studied probabilistic models that can represent uncertain futures, such models are either extremely expensive computationally (as in the case of pixel-level autoregressive models), or do not directly optimize the likelihood of the data. In this work, we propose a model for video prediction based on normalizing flows, which allows for direct optimization of the data likelihood, and produces high-quality stochastic predictions. To our knowledge, our work is the first to propose multi-frame video prediction with normalizing flows. We describe an approach for modeling the latent space dynamics, and demonstrate that flow-based generative models offer a viable and competitive approach to generative modeling of video.

2.An Adversarial Super-Resolution Remedy for Radar Design Trade-offs pdf

Radar is of vital importance in many fields, such as autonomous driving, safety and surveillance applications. However, it suffers from stringent constraints on its design parametrization leading to multiple trade-offs. For example, the bandwidth in FMCW radars is inversely proportional with both the maximum unambiguous range and range resolution. In this work, we introduce a new method for circumventing radar design trade-offs. We propose the use of recent advances in computer vision, more specifically generative adversarial networks (GANs), to enhance low-resolution radar acquisitions into higher resolution counterparts while maintaining the advantages of the low-resolution parametrization. The capability of the proposed method was evaluated on the velocity resolution and range-azimuth trade-offs in micro-Doppler signatures and FMCW uniform linear array (ULA) radars, respectively.

3.Reduced Focal Loss: 1st Place Solution to xView object detection in Satellite Imagery pdf

This paper describes our approach to the DIUx xView 2018 Detection Challenge [1]. This challenge focuses on a new satellite imagery dataset. The dataset contains 60 object classes that are highly imbalanced. Due to the imbalanced nature of the dataset, the training process becomes significantly more challenging. To address this problem, we introduce a novel Reduced Focal Loss function, which brought us 1st place in the DIUx xView 2018 Detection Challenge.

4.Joint segmentation and classification of retinal arteries/veins from fundus images pdf

Objective Automatic artery/vein (A/V) segmentation from fundus images is required to track blood vessel changes occurring with many pathologies including retinopathy and cardiovascular pathologies. One of the clinical measures that quantifies vessel changes is the arterio-venous ratio (AVR) which represents the ratio between artery and vein diameters. This measure significantly depends on the accuracy of vessel segmentation and classification into arteries and veins. This paper proposes a fast, novel method for semantic A/V segmentation combining deep learning and graph propagation.
Methods A convolutional neural network (CNN) is proposed to jointly segment and classify vessels into arteries and veins. The initial CNN labeling is propagated through a graph representation of the retinal vasculature, whose nodes are defined as the vessel branches and edges are weighted by the cost of linking pairs of branches. To efficiently propagate the labels, the graph is simplified into its minimum spanning tree.
Results The method achieves an accuracy of 94.8% for vessels segmentation. The A/V classification achieves a specificity of 92.9% with a sensitivity of 93.7% on the CT-DRIVE database compared to the state-of-the-art-specificity and sensitivity, both of 91.7%.
Conclusion The results show that our method outperforms the leading previous works on a public dataset for A/V classification and is by far the fastest.
Significance The proposed global AVR calculated on the whole fundus image using our automatic A/V segmentation method can better track vessel changes associated to diabetic retinopathy than the standard local AVR calculated only around the optic disc.

5.Semi-Supervised Brain Lesion Segmentation with an Adapted Mean Teacher Model pdf

Automated brain lesion segmentation provides valuable information for the analysis and intervention of patients. In particular, methods based on convolutional neural networks (CNNs) have achieved state-of-the-art segmentation performance. However, CNNs usually require a decent amount of annotated data, which may be costly and time-consuming to obtain. Since unannotated data is generally abundant, it is desirable to use unannotated data to improve the segmentation performance for CNNs when limited annotated data is available. In this work, we propose a semi-supervised learning (SSL) approach to brain lesion segmentation, where unannotated data is incorporated into the training of CNNs. We adapt the mean teacher model, which is originally developed for SSL-based image classification, for brain lesion segmentation. Assuming that the network should produce consistent outputs for similar inputs, a loss of segmentation consistency is designed and integrated into a self-ensembling framework. Specifically, we build a student model and a teacher model, which share the same CNN architecture for segmentation. The student and teacher models are updated alternately. At each step, the student model learns from the teacher model by minimizing the weighted sum of the segmentation loss computed from annotated data and the segmentation consistency loss between the teacher and student models computed from unannotated data. Then, the teacher model is updated by combining the updated student model with the historical information of teacher models using an exponential moving average strategy. For demonstration, the proposed approach was evaluated on ischemic stroke lesion segmentation, where it improves stroke lesion segmentation with the incorporation of unannotated data.

6.Understanding the Mechanism of Deep Learning Framework for Lesion Detection in Pathological Images with Breast Cancer pdf

The computer-aided detection (CADe) systems are developed to assist pathologists in slide assessment, increasing diagnosis efficiency and reducing missing inspections. Many studies have shown such a CADe system with deep learning approaches outperforms the one using conventional methods that rely on hand-crafted features based on field-knowledge. However, most developers who adopted deep learning models directly focused on the efficacy of outcomes, without providing comprehensive explanations on why their proposed frameworks can work effectively. In this study, we designed four experiments to verify the consecutive concepts, showing that the deep features learned from pathological patches are interpretable by domain knowledge of pathology and enlightening for clinical diagnosis in the task of lesion detection. The experimental results show the activation features work as morphological descriptors for specific cells or tissues, which agree with the clinical rules in classification. That is, the deep learning framework not only detects the distribution of tumor cells but also recognizes lymphocytes, collagen fibers, and some other non-cell structural tissues. Most of the characteristics learned by the deep learning models have summarized the detection rules that can be recognized by the experienced pathologists, whereas there are still some features may not be intuitive to domain experts but discriminative in classification for machines. Those features are worthy to be further studied in order to find out the reasonable correlations to pathological knowledge, from which pathological experts may draw inspirations for exploring new characteristics in diagnosis.

7.Unsupervised Domain Adaptation Learning Algorithm for RGB-D Staircase Recognition pdf

Detection and recognition of staircase as upstairs, downstairs and negative (e.g., ladder) are the fundamental of assisting the visually impaired to travel independently in unfamiliar environments. Previous researches have focused on using massive amounts of RGB-D scene data to train traditional machine learning (ML) based models to detect and recognize the staircase. However, the performance of traditional ML techniques is limited by the amount of labeled RGB-D staircase data. In this paper, we apply an unsupervised domain adaptation approach in deep architectures to transfer knowledge learned from the labeled RGB-D stationary staircase dataset to the unlabeled RGB-D escalator dataset. By utilizing the domain adaptation method, our feedforward convolutional neural networks (CNN) based feature extractor with 5 convolution layers can achieve 100% classification accuracy on testing the labeled stationary staircase data and 80.6% classification accuracy on testing the unlabeled escalator data. We demonstrate the success of the approach for classifying staircase on two domains with a limited amount of data. To further demonstrate the effectiveness of the approach, we also validate the same CNN model without domain adaptation and compare its results with those of our proposed architecture.

8.Collaborative Spatio-temporal Feature Learning for Video Action Recognition pdf

Spatio-temporal feature learning is of central importance for action recognition in videos. Existing deep neural network models either learn spatial and temporal features independently (C2D) or jointly with unconstrained parameters (C3D). In this paper, we propose a novel neural operation which encodes spatio-temporal features collaboratively by imposing a weight-sharing constraint on the learnable parameters. In particular, we perform 2D convolution along three orthogonal views of volumetric video data,which learns spatial appearance and temporal motion cues respectively. By sharing the convolution kernels of different views, spatial and temporal features are collaboratively learned and thus benefit from each other. The complementary features are subsequently fused by a weighted summation whose coefficients are learned end-to-end. Our approach achieves state-of-the-art performance on large-scale benchmarks and won the 1st place in the Moments in Time Challenge 2018. Moreover, based on the learned coefficients of different views, we are able to quantify the contributions of spatial and temporal features. This analysis sheds light on interpretability of the model and may also guide the future design of algorithm for video recognition.

9.STEFANN: Scene Text Editor using Font Adaptive Neural Network pdf

Textual information in a captured scene play important role in scene interpretation and decision making. Pieces of dedicated research work are going on to detect and recognize textual data accurately in images. Though there exist methods that can successfully detect complex text regions present in a scene, to the best of our knowledge there is no work to modify the textual information in an image. This paper deals with a simple text editor that can edit/modify the textual part in an image. Apart from error correction in the text part of the image, this work can directly increase the reusability of images drastically. In this work, at first, we focus on the problem to generate unobserved characters with the similar font and color of an observed text character present in a natural scene with minimum user intervention. To generate the characters, we propose a multi-input neural network that adapts the font-characteristics of a given characters (source), and generate desired characters (target) with similar font features. We also propose a network that transfers color from source to target character without any visible distortion. Next, we place the generated character in a word for its modification maintaining the visual consistency with the other characters in the word. The proposed method is a unified platform that can work like a simple text editor and edit texts in images. We tested our methodology on popular ICDAR 2011 and ICDAR 2013 datasets and results are reported here.

10.PanopticFusion: Online Volumetric Semantic Mapping at the Level of Stuff and Things pdf

We propose PanopticFusion, a novel online volumetric semantic mapping system at the level of stuff and things. In contrast to previous semantic mapping systems, PanopticFusion is able to densely predict class labels of a background region (stuff) and individually segment arbitrary foreground objects (things). In addition, our system has the capability to reconstruct a large-scale scene and extract a labeled mesh thanks to its use of a spatially hashed volumetric map representation. Our system first predicts pixel-wise panoptic labels (class labels for stuff regions and instance IDs for thing regions) for incoming RGB frames by fusing 2D semantic and instance segmentation outputs. The predicted panoptic labels are integrated into the volumetric map together with depth measurements while keeping the consistency of the instance IDs, which could vary frame to frame, by referring to the 3D map at that moment. In addition, we construct a fully connected conditional random field (CRF) model with respect to panoptic labels for map regularization. For online CRF inference, we propose a novel unary potential approximation and a map division strategy.
We evaluated the performance of our system on the ScanNet (v2) dataset. PanopticFusion outperformed or compared with state-of-the-art offline 3D DNN methods in both semantic and instance segmentation benchmarks. Also, we demonstrate a promising augmented reality application using a 3D panoptic map generated by the proposed system.

11.Zero-Shot Task Transfer pdf

In this work, we present a novel meta-learning algorithm, i.e. TTNet, that regresses model parameters for novel tasks for which no ground truth is available (zero-shot tasks). In order to adapt to novel zero-shot tasks, our meta-learner learns from the model parameters of known tasks (with ground truth) and the correlation of known tasks to zero-shot tasks. Such intuition finds its foothold in cognitive science, where a subject (human baby) can adapt to a novel-concept (depth understanding) by correlating it with old concepts (hand movement or self-motion), without receiving explicit supervision. We evaluated our model on the Taskonomy dataset, with four tasks as zero-shot: surface-normal, room layout, depth, and camera pose estimation. These tasks were chosen based on the data acquisition complexity and the complexity associated with the learning process using a deep network. Our proposed methodology out-performs state-of-the-art models (which use ground truth)on each of our zero-shot tasks, showing promise on zero-shot task transfer. We also conducted extensive experiments to study the various choices of our methodology, as well as showed how the proposed method can also be used in transfer learning. To the best of our knowledge, this is the firstsuch effort on zero-shot learning in the task space.

12.Automatic microscopic cell counting by use of deeply-supervised density regression model pdf

Accurately counting cells in microscopic images is important for medical diagnoses and biological studies, but manual cell counting is very tedious, time-consuming, and prone to subjective errors, and automatic counting can be less accurate than desired. To improve the accuracy of automatic cell counting, we propose here a novel method that employs deeply-supervised density regression. A fully convolutional neural network (FCNN) serves as the primary FCNN for density regression. A fully convolutional neural network (FCNN) serves as the primary FCNN for density map regression. Innovatively, a set of auxiliary FCNNs are employed to provide additional supervision for learning the intermediate layers of the primary CNN to improve network performance. In addition, the primary CNN is designed as a concatenating framework to integrate multi-scale features through shortcut connections in the network, which improves the granularity of the features extracted from the intermediate CNN layers and further supports the final density map estimation.

13.Unsupervised Cross-spectral Stereo Matching by Learning to Synthesize pdf

Unsupervised cross-spectral stereo matching aims at recovering disparity given cross-spectral image pairs without any supervision in the form of ground truth disparity or depth. The estimated depth provides additional information complementary to individual semantic features, which can be helpful for other vision tasks such as tracking, recognition and detection. However, there are large appearance variations between images from different spectral bands, which is a challenge for cross-spectral stereo matching. Existing deep unsupervised stereo matching methods are sensitive to the appearance variations and do not perform well on cross-spectral data. We propose a novel unsupervised cross-spectral stereo matching framework based on image-to-image translation. First, a style adaptation network transforms images across different spectral bands by cycle consistency and adversarial learning, during which appearance variations are minimized. Then, a stereo matching network is trained with image pairs from the same spectra using view reconstruction loss. At last, the estimated disparity is utilized to supervise the spectral-translation network in an end-to-end way. Moreover, a novel style adaptation network F-cycleGAN is proposed to improve the robustness of spectral translation. Our method can tackle appearance variations and enhance the robustness of unsupervised cross-spectral stereo matching. Experimental results show that our method achieves good performance without using depth supervision or explicit semantic information.

14.COMIC: Towards A Compact Image Captioning Model with Attention pdf

Recent works in image captioning have shown very promising raw performance. However, we realize that most of these encoder-decoder style networks with attention do not scale naturally to large vocabulary size, making them difficult to be deployed on embedded system with limited hardware resources. This is because the size of word and output embedding matrices grow proportionally with the size of vocabulary, adversely affecting the compactness of these networks. To address this limitation, this paper introduces a brand new idea in the domain of image captioning. That is, we tackle the problem of compactness of image captioning models which is hitherto unexplored. We showed that, our proposed model, named COMIC for COMpact Image Captioning, achieves comparable results in five common evaluation metrics with state-of-the-art approaches on both MS-COCO and InstaPIC-1.1M datasets despite having an embedding vocabulary size that is 39x - 99x smaller.

15.Incremental Visual-Inertial 3D Mesh Generation with Structural Regularities pdf

Visual-Inertial Odometry (VIO) algorithms typically rely on a point cloud representation of the scene that does not model the topology of the environment. A 3D mesh instead offers a richer, yet lightweight, model. Nevertheless, building a 3D mesh out of the sparse and noisy 3D landmarks triangulated by a VIO algorithm often results in a mesh that does not fit the real scene. In order to regularize the mesh, previous approaches decouple state estimation from the 3D mesh regularization step, and either limit the 3D mesh to the current frame or let the mesh grow indefinitely. We propose instead to tightly couple mesh regularization and state estimation by detecting and enforcing structural regularities in a novel factor-graph formulation. We also propose to incrementally build the mesh by restricting its extent to the time-horizon of the VIO optimization; the resulting 3D mesh covers a larger portion of the scene than a per-frame approach while its memory usage and computational complexity remain bounded. We show that our approach successfully regularizes the mesh, while improving localization accuracy, when structural regularities are present, and remains operational in scenes without regularities.

16.Spatiotemporal Pyramid Network for Video Action Recognition pdf

Two-stream convolutional networks have shown strong performance in video action recognition tasks. The key idea is to learn spatiotemporal features by fusing convolutional networks spatially and temporally. However, it remains unclear how to model the correlations between the spatial and temporal structures at multiple abstraction levels. First, the spatial stream tends to fail if two videos share similar backgrounds. Second, the temporal stream may be fooled if two actions resemble in short snippets, though appear to be distinct in the long term. We propose a novel spatiotemporal pyramid network to fuse the spatial and temporal features in a pyramid structure such that they can reinforce each other. From the architecture perspective, our network constitutes hierarchical fusion strategies which can be trained as a whole using a unified spatiotemporal loss. A series of ablation experiments support the importance of each fusion strategy. From the technical perspective, we introduce the spatiotemporal compact bilinear operator into video analysis tasks. This operator enables efficient training of bilinear fusion operations which can capture full interactions between the spatial and temporal features. Our final network achieves state-of-the-art results on standard video datasets.

17.Active Authentication using an Autoencoder regularized CNN-based One-Class Classifier pdf

Active authentication refers to the process in which users are unobtrusively monitored and authenticated continuously throughout their interactions with mobile devices. Generally, an active authentication problem is modelled as a one class classification problem due to the unavailability of data from the impostor users. Normally, the enrolled user is considered as the target class (genuine) and the unauthorized users are considered as unknown classes (impostor). We propose a convolutional neural network (CNN) based approach for one class classification in which a zero centered Gaussian noise and an autoencoder are used to model the pseudo-negative class and to regularize the network to learn meaningful feature representations for one class data, respectively. The overall network is trained using a combination of the cross-entropy and the reconstruction error losses. A key feature of the proposed approach is that any pre-trained CNN can be used as the base network for one class classification. Effectiveness of the proposed framework is demonstrated using three publically available face-based active authentication datasets and it is shown that the proposed method achieves superior performance compared to the traditional one class classification methods. The source code is available at: github.com/otkupjnoz/oc-acnn.

18.A Kernelized Manifold Mapping to Diminish the Effect of Adversarial Perturbations pdf

The linear and non-flexible nature of deep convolutional models makes them vulnerable to carefully crafted adversarial perturbations. To tackle this problem, we propose a non-linear radial basis convolutional feature mapping by learning a Mahalanobis-like distance function. Our method then maps the convolutional features onto a linearly well-separated manifold, which prevents small adversarial perturbations from forcing a sample to cross the decision boundary. We test the proposed method on three publicly available image classification and segmentation datasets namely, MNIST, ISBI ISIC 2017 skin lesion segmentation, and NIH Chest X-Ray-14. We evaluate the robustness of our method to different gradient (targeted and untargeted) and non-gradient based attacks and compare it to several non-gradient masking defense strategies. Our results demonstrate that the proposed method can increase the resilience of deep convolutional neural networks to adversarial perturbations without accuracy drop on clean data.

19.Hand Pose Estimation: A Survey pdf

The success of Deep Convolutional Neural Networks (CNNs) in recent years in almost all the Computer Vision tasks on one hand, and the popularity of low-cost consumer depth cameras on the other, has made Hand Pose Estimation a hot topic in computer vision field. In this report, we will first explain the hand pose estimation problem and will review major approaches solving this problem, especially the two different problems of using depth maps or RGB images. We will survey the most important papers in each field and will discuss the strengths and weaknesses of each. Finally, we will explain the biggest datasets in this field in detail and list 21 datasets with all their properties. To the best of our knowledge this is the most complete list of all the datasets in the hand pose estimation field.

20.Self-Supervised Learning of Face Representations for Video Face Clustering pdf

Analyzing the story behind TV series and movies often requires understanding who the characters are and what they are doing. With improving deep face models, this may seem like a solved problem. However, as face detectors get better, clustering/identification needs to be revisited to address increasing diversity in facial appearance. In this paper, we address video face clustering using unsupervised methods. Our emphasis is on distilling the essential information, identity, from the representations obtained using deep pre-trained face networks. We propose a self-supervised Siamese network that can be trained without the need for video/track based supervision, and thus can also be applied to image collections. We evaluate our proposed method on three video face clustering datasets. The experiments show that our methods outperform current state-of-the-art methods on all datasets. Video face clustering is lacking a common benchmark as current works are often evaluated with different metrics and/or different sets of face tracks.

21.X-Section: Cross-section Prediction for Enhanced RGBD Fusion pdf

Detailed 3D reconstruction is an important challenge with application to robotics, augmented and virtual reality, which has seen impressive progress throughout the past years. Advancements were driven by the availability of depth cameras (RGB-D), as well as increased compute power, e.g.\ in the form of GPUs -- but also thanks to inclusion of machine learning in the process. Here, we propose X-Section, an RGB-D 3D reconstruction approach that leverages deep learning to make object-level predictions about thicknesses that can be readily integrated into a volumetric multi-view fusion process, where we propose an extension to the popular KinectFusion approach. In essence, our method allows to complete shape in general indoor scenes behind what is sensed by the RGB-D camera, which may be crucial e.g.\ for robotic manipulation tasks or efficient scene exploration. Predicting object thicknesses rather than volumes allows us to work with comparably high spatial resolution without exploding memory and training data requirements on the employed Convolutional Neural Networks. In a series of qualitative and quantitative evaluations, we demonstrate how we accurately predict object thickness and reconstruct general 3D scenes containing multiple objects.

22.Matching Thermal to Visible Face Images Using a Semantic-Guided Generative Adversarial Network pdf

Designing face recognition systems that are capable of matching face images obtained in the thermal spectrum with those obtained in the visible spectrum is a challenging problem. In this work, we propose the use of semantic-guided generative adversarial network (SG-GAN) to automatically synthesize visible face images from their thermal counterparts. Specifically, semantic labels, extracted by a face parsing network, are used to compute a semantic loss function to regularize the adversarial network during training. These semantic cues denote high-level facial component information associated with each pixel. Further, an identity extraction network is leveraged to generate multi-scale features to compute an identity loss function. To achieve photo-realistic results, a perceptual loss function is introduced during network training to ensure that the synthesized visible face is perceptually similar to the target visible face image. We extensively evaluate the benefits of individual loss functions, and combine them effectively to learn the mapping from thermal to visible face images. Experiments involving two multispectral face datasets show that the proposed method achieves promising results in both face synthesis and cross-spectral face matching.

23.Probability Map Guided Bi-directional Recurrent UNet for Pancreas Segmentation pdf

Pancreatic cancer is one of the most lethal cancers as incidence approximates mortality. A method for accurately segmenting the pancreas can assist doctors in the diagnosis and treatment of pancreatic cancer. In the current widely used approaches, the 2D method ignores the spatial information of the pancreas, and the 3D model is limited by high resource consumption and GPU memory occupancy. To address these issues, we propose a bi-directional recurrent UNet (PBR-UNet) based on probability graph guidance, which consists of a feature extraction network for efficiently extracting pixel-level probability map as guidance and a bi-directional recurrent network for precise segmentation. The context information of adjacent slices is interconnected to form a chain structure. We integrate contextual information into the entire segmentation network through bi-directional loops to avoid the loss of spatial information in propagation. Additionally, an iterator is applied in the process of propagation, which is used to update the guided probability map after each propagation. We solve the problem that the 2D network loses three-dimensional information and combines the probability map of the adjacent slices into the segmentation as spatial information, avoiding large computational resource consumption caused by direct use of the 3D network. We used Dice similarity coefficients (DSC) to evaluate our approach on NIH pancreatic datasets and eventually achieved a competitive result of 83.02%.

24.Unsupervised Bi-directional Flow-based Video Generation from one Snapshot pdf

Imagining multiple consecutive frames given one single snapshot is challenging, since it is difficult to simultaneously predict diverse motions from a single image and faithfully generate novel frames without visual distortions. In this work, we leverage an unsupervised variational model to learn rich motion patterns in the form of long-term bi-directional flow fields, and apply the predicted flows to generate high-quality video sequences. In contrast to the state-of-the-art approach, our method does not require external flow supervisions for learning. This is achieved through a novel module that performs bi-directional flows prediction from a single image. In addition, with the bi-directional flow consistency check, our method can handle occlusion and warping artifacts in a principled manner. Our method can be trained end-to-end based on arbitrarily sampled natural video clips, and it is able to capture multi-modal motion uncertainty and synthesizes photo-realistic novel sequences. Quantitative and qualitative evaluations over synthetic and real-world datasets demonstrate the effectiveness of the proposed approach over the state-of-the-art methods.

25.Ground Plane based Absolute Scale Estimation for Monocular Visual Odometry pdf

Recovering the absolute metric scale from a monocular camera is a challenging but highly desirable problem for monocular camera-based systems. By using different kinds of cues, various approaches have been proposed for scale estimation, such as camera height, object size etc. In this paper, firstly, we summarize different kinds of scale estimation approaches. Then, we propose a robust divide and conquer the absolute scale estimation method based on the ground plane and camera height by analyzing the advantages and disadvantages of different approaches. By using the estimated scale, an effective scale correction strategy has been proposed to reduce the scale drift during the Monocular Visual Odometry (VO) estimation process. Finally, the effectiveness and robustness of the proposed method have been verified on both public and self-collected image sequences.

26.MILDNet: A Lightweight Single Scaled Deep Ranking Architecture pdf

Multi-scale deep CNN architecture [1, 2, 3] successfully captures both fine and coarse level image descriptors for visual similarity task, but they come up with expensive memory overhead and latency. In this paper, we propose a competing novel CNN architecture, called MILDNet, which merits by being vastly compact (about 3 times). Inspired by the fact that successive CNN layers represent the image with increasing levels of abstraction, we compressed our deep ranking model to a single CNN by coupling activations from multiple intermediate layers along with the last layer. Trained on the famous Street2shop dataset [4], we demonstrate that our approach performs as good as the current state-of-the-art models with only one third of the parameters, model size, training time and significant reduction in inference time. The significance of intermediate layers on image retrieval task has also been shown to be performing on popular datasets Holidays, Oxford, Paris [5]. So even though our experiments are done on ecommerce domain, it is applicable to other domains as well. We further did an ablation study to validate our hypothesis by checking the impact on adding each intermediate layer. With this we also present two more useful variants of MILDNet, a mobile model (12 times smaller) for on-edge devices and a compactly featured model (512-d feature embeddings) for systems with less RAMs and to reduce the ranking cost. Further we present an intuitive way to automatically create a tailored in-house triplet training dataset, which is very hard to create manually. This solution too can also be deployed as an all-inclusive visual similarity solution. Finally, we present our entire production level architecture which currently powers visual similarity at Fynd.

27.3D convolutional neural network for abdominal aortic aneurysm segmentation pdf

An abdominal aortic aneurysm (AAA) is a focal dilation of the aorta that, if not treated, tends to grow and may rupture. A significant unmet need in the assessment of AAA disease, for the diagnosis, prognosis and follow-up, is the determination of rupture risk, which is currently based on the manual measurement of the aneurysm diameter in a selected Computed Tomography Angiography (CTA) scan. However, there is a lack of standardization determining the degree and rate of disease progression, due to the lack of robust, automated aneurysm segmentation tools that allow quantitatively analyzing the AAA. In this work, we aim at proposing the first 3D convolutional neural network for the segmentation of aneurysms both from preoperative and postoperative CTA scans. We extensively validate its performance in terms of diameter measurements, to test its applicability in the clinical practice, as well as regarding the relative volume difference, and Dice and Jaccard scores. The proposed method yields a mean diameter measurement error of 3.3 mm, a relative volume difference of 8.58 %, and Dice and Jaccard scores of 87 % and 77 %, respectively. At a clinical level, an aneurysm enlargement of 10 mm is considered relevant, thus, our method is suitable to automatically determine the AAA diameter and opens up the opportunity for more complex aneurysm analysis.

28.Meta-SR: A Magnification-Arbitrary Network for Super-Resolution pdf

Recent research on super-resolution has achieved great success due to the development of deep convolutional neural networks (DCNNs). However, super-resolution of arbitrary scale factor has been ignored for a long time. Most previous researchers regard super-resolution of different scale factors as independent tasks. They train a specific model for each scale factor which is inefficient in computing, and prior work only take the super-resolution of several integer scale factors into consideration. In this work, we propose a novel method called Meta-SR to firstly solve super-resolution of arbitrary scale factor (including non-integer scale factors) with a single model. In our Meta-SR, the Meta-Upscale Module is proposed to replace the traditional upscale module. For arbitrary scale factor, the Meta-Upscale Module dynamically predicts the weights of the upscale filters by taking the scale factor as input and use these weights to generate the HR image of arbitrary size. For any low-resolution image, our Meta-SR can continuously zoom in it with arbitrary scale factor by only using a single model. We evaluated the proposed method through extensive experiments on widely used benchmark datasets on single image super-resolution. The experimental results show the superiority of our Meta-Upscale.

29.Face Image Reflection Removal pdf

Face images captured through the glass are usually contaminated by reflections. The non-transmitted reflections make the reflection removal more challenging than for general scenes, because important facial features are completely occluded. In this paper, we propose and solve the face image reflection removal problem. We remove non-transmitted reflections by incorporating inpainting ideas into a guided reflection removal framework and recover facial features by considering various face-specific priors. We use a newly collected face reflection image dataset to train our model and compare with state-of-the-art methods. The proposed method shows advantages in estimating reflection-free face images for improving face recognition.

30.Less is More: Learning Highlight Detection from Video Duration pdf

Highlight detection has the potential to significantly ease video browsing, but existing methods often suffer from expensive supervision requirements, where human viewers must manually identify highlights in training videos. We propose a scalable unsupervised solution that exploits video duration as an implicit supervision signal. Our key insight is that video segments from shorter user-generated videos are more likely to be highlights than those from longer videos, since users tend to be more selective about the content when capturing shorter videos. Leveraging this insight, we introduce a novel ranking framework that prefers segments from shorter videos, while properly accounting for the inherent noise in the (unlabeled) training data. We use it to train a highlight detector with 10M hashtagged Instagram videos. In experiments on two challenging public video highlight detection benchmarks, our method substantially improves the state-of-the-art for unsupervised highlight detection.

31.Recognition of Multiple Food Items in a Single Photo for Use in a Buffet-Style Restaurant pdf

We investigate image recognition of multiple food items in a single photo, focusing on a buffet restaurant application, where menu changes at every meal, and only a few images per class are available. After detecting food areas, we perform hierarchical recognition. We evaluate our results, comparing to two baseline methods.

32.CAD-Net: A Context-Aware Detection Network for Objects in Remote Sensing Imagery pdf

Accurate and robust detection of multi-class objects in optical remote sensing images is essential to many real-world applications such as urban planning, traffic control, searching and rescuing, etc. However, state-of-the-art object detection techniques designed for images captured using ground-level sensors usually experience a sharp performance drop when directly applied to remote sensing images, largely due to the object appearance differences in remote sensing images in term of sparse texture, low contrast, arbitrary orientations, large scale variations, etc. This paper presents a novel object detection network (CAD-Net) that exploits attention-modulated features as well as global and local contexts to address the new challenges in detecting objects from remote sensing images. The proposed CAD-Net learns global and local contexts of objects by capturing their correlations with the global scene (at scene-level) and the local neighboring objects or features (at object-level), respectively. In addition, it designs a spatial-and-scale-aware attention module that guides the network to focus on more informative regions and features as well as more appropriate feature scales. Experiments over two publicly available object detection datasets for remote sensing images demonstrate that the proposed CAD-Net achieves superior detection performance. The implementation codes will be made publicly available for facilitating future researches.

33.Crowd Counting and Density Estimation by Trellis Encoder-Decoder Network pdf

Crowd counting has recently attracted increasing interest in computer vision but remains a challenging problem. In this paper, we propose a trellis encoder-decoder network (TEDnet) for crowd counting, which focuses on generating high-quality density estimation maps. The major contributions are four-fold. First, we develop a new trellis architecture that incorporates multiple decoding paths to hierarchically aggregate features at different encoding stages, which can handle large variations of objects. Second, we design dense skip connections interleaved across paths to facilitate sufficient multi-scale feature fusions and to absorb the supervision information. Third, we propose a new combinatorial loss to enforce local coherence and spatial correlation in density maps. By distributedly imposing this combinatorial loss on intermediate outputs, gradient vanishing can be largely alleviated for better back-propagation and faster convergence. Finally, our TEDnet achieves new state-of-the art performance on four benchmarks, with an improvement up to 14% in terms of MAE.

34.Improving Referring Expression Grounding with Cross-modal Attention-guided Erasing pdf

Referring expression grounding aims at locating certain objects or persons in an image with a referring expression, where the key challenge is to comprehend and align various types of information from visual and textual domain, such as visual attributes, location and interactions with surrounding regions. Although the attention mechanism has been successfully applied for cross-modal alignments, previous attention models focus on only the most dominant features of both modalities, and neglect the fact that there could be multiple comprehensive textual-visual correspondences between images and referring expressions. To tackle this issue, we design a novel cross-modal attention-guided erasing approach, where we discard the most dominant information from either textual or visual domains to generate difficult training samples online, and to drive the model to discover complementary textual-visual correspondences. Extensive experiments demonstrate the effectiveness of our proposed method, which achieves state-of-the-art performance on three referring expression grounding datasets.

35.Image Super-Resolution by Neural Texture Transfer pdf

Due to the significant information loss in low-resolution (LR) images, it has become extremely challenging to further advance the state-of-the-art of single image super-resolution (SISR). Reference-based super-resolution (RefSR), on the other hand, has proven to be promising in recovering high-resolution (HR) details when a reference (Ref) image with similar content as that of the LR input is given. However, the quality of RefSR can degrade severely when Ref is less similar. This paper aims to unleash the potential of RefSR by leveraging more texture details from Ref images with stronger robustness even when irrelevant Ref images are provided. Inspired by the recent work on image stylization, we formulate the RefSR problem as neural texture transfer. We design an end-to-end deep model which enriches HR details by adaptively transferring the texture from Ref images according to their textural similarity. Instead of matching content in the raw pixel space as done by previous methods, our key contribution is a multi-level matching conducted in the neural space. This matching scheme facilitates multi-scale neural transfer that allows the model to benefit more from those semantically related Ref patches, and gracefully degrade to SISR performance on the least relevant Ref inputs. We build a benchmark dataset for the general research of RefSR, which contains Ref images paired with LR inputs with varying levels of similarity. Both quantitative and qualitative evaluations demonstrate the superiority of our method over state-of-the-art.

36.Pancreas Segmentation via Spatial Context based U-net and Bidirectional LSTM pdf

Pancreas is characterized by small size and irregular shape, so achieving accurate pancreas segmentation is challenging. Traditional 2D pancreas segmentation network based on the independent 2D image slices, which often leads to spatial discontinuity problem. Therefore, how to utility spatial context information is the key point to improve the segmentation quality. In this paper, we proposed a divide-and-conquer strategy, divided the abdominal CT scans into several isometric blocks. And we designed a multiple channels convolutional neural network to learn the local spatial context characteristics from blocks called SCU-Net. SCU-Net is a partial 3D segmentation idea, which transforms overall pancreas segmentation into a combination of multiple local segmentation results. In order to improve the segmentation accuracy for each layer, we also proposed a new loss function for inter-slice constrain and regularization. Thereafter, we introduced the BiCLSTM network for stimulating the interaction between bidirectional segmentation sequence, thus making up the boundary defect and fault problem of the segmentation results. We trained SCU-Net+BiLSTM network respectively, and evaluated segmentation result on the NIH data set. Keywords: Pancreas Segmentation, Convolutional Neural Networks, Recurrent Neural Networks, Deep Learning, Inter-slice Regularization

37.3D Hand Shape and Pose Estimation from a Single RGB Image pdf

This work addresses a novel and challenging problem of estimating the full 3D hand shape and pose from a single RGB image. Most current methods in 3D hand analysis from monocular RGB images only focus on estimating the 3D locations of hand keypoints, which cannot fully express the 3D shape of hand. In contrast, we propose a Graph Convolutional Neural Network (Graph CNN) based method to reconstruct a full 3D mesh of hand surface that contains richer information of both 3D hand shape and pose. To train networks with full supervision, we create a large-scale synthetic dataset containing both ground truth 3D meshes and 3D poses. When fine-tuning the networks on real-world datasets without 3D ground truth, we propose a weakly-supervised approach by leveraging the depth map as a weak supervision in training. Through extensive evaluations on our proposed new datasets and two public datasets, we show that our proposed method can produce accurate and reasonable 3D hand mesh, and can achieve superior 3D hand pose estimation accuracy when compared with state-of-the-art methods.

38.Let's Transfer Transformations of Shared Semantic Representations pdf

With a good image understanding capability, can we manipulate the images high level semantic representation? Such transformation operation can be used to generate or retrieve similar images but with a desired modification (for example changing beach background to street background); similar ability has been demonstrated in zero shot learning, attribute composition and attribute manipulation image search. In this work we show how one can learn transformations with no training examples by learning them on another domain and then transfer to the target domain. This is feasible if: first, transformation training data is more accessible in the other domain and second, both domains share similar semantics such that one can learn transformations in a shared embedding space. We demonstrate this on an image retrieval task where search query is an image, plus an additional transformation specification (for example: search for images similar to this one but background is a street instead of a beach). In one experiment, we transfer transformation from synthesized 2D blobs image to 3D rendered image, and in the other, we transfer from text domain to natural image domain.

39.AIRD: Adversarial Learning Framework for Image Repurposing Detection pdf

Image repurposing is a commonly used method for spreading misinformation on social media and online forums, which involves publishing untampered images with modified metadata to create rumors and further propaganda. While manual verification is possible, given vast amounts of verified knowledge available on the internet, the increasing prevalence and ease of this form of semantic manipulation call for the development of robust automatic ways of assessing the semantic integrity of multimedia data. In this paper, we present a novel method for image repurposing detection that is based on the real-world adversarial interplay between a bad actor who repurposes images with counterfeit metadata and a watchdog who verifies the semantic consistency between images and their accompanying metadata, where both players have access to a reference dataset of verified content, which they can use to achieve their goals. The proposed method exhibits state-of-the-art performance on location-identity, subject-identity and painting-artist verification, showing its efficacy across a diverse set of scenarios.

40.Spatio-Temporal Vegetation Pixel Classification By Using Convolutional Networks pdf

Plant phenology studies rely on long-term monitoring of life cycles of plants. High-resolution unmanned aerial vehicles (UAVs) and near-surface technologies have been used for plant monitoring, demanding the creation of methods capable of locating and identifying plant species through time and space. However, this is a challenging task given the high volume of data, the constant data missing from temporal dataset, the heterogeneity of temporal profiles, the variety of plant visual patterns, and the unclear definition of individuals' boundaries in plant communities. In this letter, we propose a novel method, suitable for phenological monitoring, based on Convolutional Networks (ConvNets) to perform spatio-temporal vegetation pixel-classification on high resolution images. We conducted a systematic evaluation using high-resolution vegetation image datasets associated with the Brazilian Cerrado biome. Experimental results show that the proposed approach is effective, overcoming other spatio-temporal pixel-classification strategies.

41.Extreme Channel Prior Embedded Network for Dynamic Scene Deblurring pdf

Recent years have witnessed the significant progress on convolutional neural networks (CNNs) in dynamic scene deblurring. While CNN models are generally learned by the reconstruction loss defined on training data, incorporating suitable image priors as well as regularization terms into the network architecture could boost the deblurring performance. In this work, we propose an Extreme Channel Prior embedded Network (ECPeNet) to plug the extreme channel priors (i.e., priors on dark and bright channels) into a network architecture for effective dynamic scene deblurring. A novel trainable extreme channel prior embedded layer (ECPeL) is developed to aggregate both extreme channel and blurry image representations, and sparse regularization is introduced to regularize the ECPeNet model learning. Furthermore, we present an effective multi-scale network architecture that works in both coarse-to-fine and fine-to-coarse manners for better exploiting information flow across scales. Experimental results on GoPro and Kohler datasets show that our proposed ECPeNet performs favorably against state-of-the-art deep image deblurring methods in terms of both quantitative metrics and visual quality.

42.PartNet: A Recursive Part Decomposition Network for Fine-grained and Hierarchical Shape Segmentation pdf

Deep learning approaches to 3D shape segmentation are typically formulated as a multi-class labeling problem. Existing models are trained for a fixed set of labels, which greatly limits their flexibility and adaptivity. We opt for top-down recursive decomposition and develop the first deep learning model for hierarchical segmentation of 3D shapes, based on recursive neural networks. Starting from a full shape represented as a point cloud, our model performs recursive binary decomposition, where the decomposition network at all nodes in the hierarchy share weights. At each node, a node classifier is trained to determine the type (adjacency or symmetry) and stopping criteria of its decomposition. The features extracted in higher level nodes are recursively propagated to lower level ones. Thus, the meaningful decompositions in higher levels provide strong contextual cues constraining the segmentations in lower levels. Meanwhile, to increase the segmentation accuracy at each node, we enhance the recursive contextual feature with the shape feature extracted for the corresponding part. Our method segments a 3D shape in point cloud into an unfixed number of parts, depending on the shape complexity, showing strong generality and flexibility. It achieves the state-of-the-art performance, both for fine-grained and semantic segmentation, on the public benchmark and a new benchmark of fine-grained segmentation proposed in this work. We also demonstrate its application for fine-grained part refinements in image-to-shape reconstruction.

43.Deep Optimization model for Screen Content Image Quality Assessment using Neural Networks pdf

In this paper, we propose a novel quadratic optimized model based on the deep convolutional neural network (QODCNN) for full-reference and no-reference screen content image (SCI) quality assessment. Unlike traditional CNN methods taking all image patches as training data and using average quality pooling, our model is optimized to obtain a more effective model including three steps. In the first step, an end-to-end deep CNN is trained to preliminarily predict the image visual quality, and batch normalized (BN) layers and l2 regularization are employed to improve the speed and performance of network fitting. For second step, the pretrained model is fine-tuned to achieve better performance under analysis of the raw training data. An adaptive weighting method is proposed in the third step to fuse local quality inspired by the perceptual property of the human visual system (HVS) that the HVS is sensitive to image patches containing texture and edge information. The novelty of our algorithm can be concluded as follows: 1) with the consideration of correlation between local quality and subjective differential mean opinion score (DMOS), the Euclidean distance is utilized to measure effectiveness of image patches, and the pretrained model is fine-tuned with more effective training data; 2) an adaptive pooling approach is employed to fuse patch quality of textual and pictorial regions, whose feature only extracted from distorted images owns strong noise robust and effects on both FR and NR IQA; 3) Considering the characteristics of SCIs, a deep and valid network architecture is designed for both NR and FR visual quality evaluation of SCIs. Experimental results verify that our model outperforms both current no-reference and full-reference image quality assessment methods on the benchmark screen content image quality assessment database (SIQAD).

44.Fine-Grained Semantic Segmentation of Motion Capture Data using Dilated Temporal Fully-Convolutional Networks pdf

Human motion capture data has been widely used in data-driven character animation. In order to generate realistic, natural-looking motions, most data-driven approaches require considerable efforts of pre-processing, including motion segmentation and annotation. Existing (semi-) automatic solutions either require hand-crafted features for motion segmentation or do not produce the semantic annotations required for motion synthesis and building large-scale motion databases. In addition, human labeled annotation data suffers from inter- and intra-labeler inconsistencies by design. We propose a semi-automatic framework for semantic segmentation of motion capture data based on supervised machine learning techniques. It first transforms a motion capture sequence into a ``motion image'' and applies a convolutional neural network for image segmentation. Dilated temporal convolutions enable the extraction of temporal information from a large receptive field. Our model outperforms two state-of-the-art models for action segmentation, as well as a popular network for sequence modeling. Most of all, our method is very robust under noisy and inaccurate training labels and thus can handle human errors during the labeling process.

45.OmniDRL: Robust Pedestrian Detection using Deep Reinforcement Learning on Omnidirectional Cameras pdf

Pedestrian detection is one of the most explored topics in computer vision and robotics. The use of deep learning methods allowed the development of new and highly competitive algorithms. Deep Reinforcement Learning has proved to be within the state-of-the-art in terms of both detection in perspective cameras and robotics applications. However, for detection in omnidirectional cameras, the literature is still scarce, mostly because of their high levels of distortion. This paper presents a novel and efficient technique for robust pedestrian detection in omnidirectional images. The proposed method uses deep Reinforcement Learning that takes advantage of the distortion in the image. By considering the 3D bounding boxes and their distorted projections into the image, our method is able to provide the pedestrian's position in the world, in contrast to the image positions provided by most state-of-the-art methods for perspective cameras. Our method avoids the need of pre-processing steps to remove the distortion, which is computationally expensive. Beyond the novel solution, our method compares favorably with the state-of-the-art methodologies that do not consider the underlying distortion for the detection task.

46.Quaternion Convolutional Neural Networks pdf

Neural networks in the real domain have been studied for a long time and achieved promising results in many vision tasks for recent years. However, the extensions of the neural network models in other number fields and their potential applications are not fully-investigated yet. Focusing on color images, which can be naturally represented as quaternion matrices, we propose a quaternion convolutional neural network (QCNN) model to obtain more representative features. In particular, we redesign the basic modules like convolution layer and fully-connected layer in the quaternion domain, which can be used to establish fully-quaternion convolutional neural networks. Moreover, these modules are compatible with almost all deep learning techniques and can be plugged into traditional CNNs easily. We test our QCNN models in both color image classification and denoising tasks. Experimental results show that they outperform the real-valued CNNs with same structures.

47.Feature Selective Anchor-Free Module for Single-Shot Object Detection pdf

We motivate and present feature selective anchor-free (FSAF) module, a simple and effective building block for single-shot object detectors. It can be plugged into single-shot detectors with feature pyramid structure. The FSAF module addresses two limitations brought up by the conventional anchor-based detection: 1) heuristic-guided feature selection; 2) overlap-based anchor sampling. The general concept of the FSAF module is online feature selection applied to the training of multi-level anchor-free branches. Specifically, an anchor-free branch is attached to each level of the feature pyramid, allowing box encoding and decoding in the anchor-free manner at an arbitrary level. During training, we dynamically assign each instance to the most suitable feature level. At the time of inference, the FSAF module can work jointly with anchor-based branches by outputting predictions in parallel. We instantiate this concept with simple implementations of anchor-free branches and online feature selection strategy. Experimental results on the COCO detection track show that our FSAF module performs better than anchor-based counterparts while being faster. When working jointly with anchor-based branches, the FSAF module robustly improves the baseline RetinaNet by a large margin under various settings, while introducing nearly free inference overhead. And the resulting best model can achieve a state-of-the-art 44.6% mAP, outperforming all existing single-shot detectors on COCO.

48.RGBD Based Dimensional Decomposition Residual Network for 3D Semantic Scene Completion pdf

RGB images differentiate from depth images as they carry more details about the color and texture information, which can be utilized as a vital complementary to depth for boosting the performance of 3D semantic scene completion (SSC). SSC is composed of 3D shape completion (SC) and semantic scene labeling while most of the existing methods use depth as the sole input which causes the performance bottleneck. Moreover, the state-of-the-art methods employ 3D CNNs which have cumbersome networks and tremendous parameters. We introduce a light-weight Dimensional Decomposition Residual network (DDR) for 3D dense prediction tasks. The novel factorized convolution layer is effective for reducing the network parameters, and the proposed multi-scale fusion mechanism for depth and color image can improve the completion and segmentation accuracy simultaneously. Our method demonstrates excellent performance on two public datasets. Compared with the latest method SSCNet, we achieve 5.9% gains in SC-IoU and 5.7% gains in SSC-IOU, albeit with only 21% network parameters and 16.6% FLOPs employed compared with that of SSCNet.

49.Unsupervised Traffic Accident Detection in First-Person Videos pdf

Recognizing abnormal events such as traffic violations and accidents in natural driving scenes is essential for successful autonomous and advanced driver assistance systems. However, most work on video anomaly detection suffers from one of two crucial drawbacks. First, it assumes cameras are fixed and videos have a static background, which is reasonable for surveillance applications but not for vehicle-mounted cameras. Second, it poses the problem as one-class classification, which relies on arduous human annotation and only recognizes categories of anomalies that have been explicitly trained. In this paper, we propose an unsupervised approach for traffic accident detection in first-person videos. Our major novelty is to detect anomalies by predicting the future locations of traffic participants and then monitoring the prediction accuracy and consistency metrics with three different strategies. To evaluate our approach, we introduce a new dataset of diverse traffic accidents, AnAn Accident Detection (A3D), as well as another publicly-available dataset. Experimental results show that our approach outperforms the state-of-the-art.

50.Straight to the point: reinforcement learning for user guidance in ultrasound pdf

Point of care ultrasound (POCUS) consists in the use of ultrasound imaging in critical or emergency situations to support clinical decisions by healthcare professionals and first responders. In this setting it is essential to be able to provide means to obtain diagnostic data to potentially inexperienced users who did not receive an extensive medical training. Interpretation and acquisition of ultrasound images is not trivial. First, the user needs to find a suitable sound window which can be used to get a clear image, and then he needs to correctly interpret it to perform a diagnosis. Although many recent approaches focus on developing smart ultrasound devices that add interpretation capabilities to existing systems, our goal in this paper is to present a reinforcement learning (RL) strategy which is capable to guide novice users to the correct sonic window and enable them to obtain clinically relevant pictures of the anatomy of interest. We apply our approach to cardiac images acquired from the parasternal long axis (PLAx) view of the left ventricle of the heart.

51.Unsupervised Tracklet Person Re-Identification pdf

Most existing person re-identification (re-id) methods rely on supervised model learning on per-camera-pair manually labelled pairwise training data. This leads to poor scalability in a practical re-id deployment, due to the lack of exhaustive identity labelling of positive and negative image pairs for every camera-pair. In this work, we present an unsupervised re-id deep learning approach. It is capable of incrementally discovering and exploiting the underlying re-id discriminative information from automatically generated person tracklet data end-to-end. We formulate an Unsupervised Tracklet Association Learning (UTAL) framework. This is by jointly learning within-camera tracklet discrimination and cross-camera tracklet association in order to maximise the discovery of tracklet identity matching both within and across camera views. Extensive experiments demonstrate the superiority of the proposed model over the state-of-the-art unsupervised learning and domain adaptation person re-id methods on eight benchmarking datasets.

52.Learning where to look: Semantic-Guided Multi-Attention Localization for Zero-Shot Learning pdf

Zero-shot learning extends the conventional object classification to the unseen class recognition by introducing semantic representations of classes. Existing approaches predominantly focus on learning the proper mapping function for visual-semantic embedding, while neglecting the effect of learning discriminative visual features. In this paper, we study the significance of the discriminative region localization. We propose a semantic-guided multi-attention localization model, which automatically discovers the most discriminative parts of objects for zero-shot learning without any human annotations. Our model jointly learns cooperative global and local features from the whole object as well as the detected parts to categorize objects based on semantic descriptions. Moreover, with the joint supervision of embedding softmax loss and class-center triplet loss, the model is encouraged to learn features with high inter-class dispersion and intra-class compactness. Through comprehensive experiments on three widely used zero-shot learning benchmarks, we show the efficacy of the multi-attention localization and our proposed approach improves the state-of-the-art results by a considerable margin.

53.PEA265: Perceptual Assessment of Video Compression Artifacts pdf

The most widely used video encoders share a common hybrid coding framework that includes block-based motion estimation/compensation and block-based transform coding. Despite their high coding efficiency, the encoded videos often exhibit visually annoying artifacts, denoted as Perceivable Encoding Artifacts (PEAs), which significantly degrade the visual Qualityof- Experience (QoE) of end users. To monitor and improve visual QoE, it is crucial to develop subjective and objective measures that can identify and quantify various types of PEAs. In this work, we make the first attempt to build a large-scale subjectlabelled database composed of H.265/HEVC compressed videos containing various PEAs. The database, namely the PEA265 database, includes 4 types of spatial PEAs (i.e. blurring, blocking, ringing and color bleeding) and 2 types of temporal PEAs (i.e. flickering and floating). Each containing at least 60,000 image or video patches with positive and negative labels. To objectively identify these PEAs, we train Convolutional Neural Networks (CNNs) using the PEA265 database. It appears that state-of-theart ResNeXt is capable of identifying each type of PEAs with high accuracy. Furthermore, we define PEA pattern and PEA intensity measures to quantify PEA levels of compressed video sequence. We believe that the PEA265 database and our findings will benefit the future development of video quality assessment methods and perceptually motivated video encoders.

54.Complement Objective Training pdf

Learning with a primary objective, such as softmax cross entropy for classification and sequence generation, has been the norm for training deep neural networks for years. Although being a widely-adopted approach, using cross entropy as the primary objective exploits mostly the information from the ground-truth class for maximizing data likelihood, and largely ignores information from the complement (incorrect) classes. We argue that, in addition to the primary objective, training also using a complement objective that leverages information from the complement classes can be effective in improving model performance. This motivates us to study a new training paradigm that maximizes the likelihood of the groundtruth class while neutralizing the probabilities of the complement classes. We conduct extensive experiments on multiple tasks ranging from computer vision to natural language understanding. The experimental results confirm that, compared to the conventional training with just one primary objective, training also with the complement objective further improves the performance of the state-of-the-art models across all tasks. In addition to the accuracy improvement, we also show that models trained with both primary and complement objectives are more robust to single-step adversarial attacks.

55.Accelerating Training of Deep Neural Networks with a Standardization Loss pdf

A significant advance in accelerating neural network training has been the development of normalization methods, permitting the training of deep models both faster and with better accuracy. These advances come with practical challenges: for instance, batch normalization ties the prediction of individual examples with other examples within a batch, resulting in a network that is heavily dependent on batch size. Layer normalization and group normalization are data-dependent and thus must be continually used, even at test-time. To address the issues that arise from using explicit normalization techniques, we propose to replace existing normalization methods with a simple, secondary objective loss that we term a standardization loss. This formulation is flexible and robust across different batch sizes and surprisingly, this secondary objective accelerates learning on the primary training objective. Because it is a training loss, it is simply removed at test-time, and no further effort is needed to maintain normalized activations. We find that a standardization loss accelerates training on both small- and large-scale image classification experiments, works with a variety of architectures, and is largely robust to training across different batch sizes.

56.End-to-end Driving Deploying through Uncertainty-Aware Imitation Learning and Stochastic Visual Domain Adaptation pdf

End-to-end visual-based imitation learning has been widely applied in autonomous driving. When deploying the trained visual-based driving policy, a deterministic command is usually directly applied without considering the uncertainty of the input data. Such kind of policies may bring dramatical damage when applied in the real world. In this paper, we follow the recent real-to-sim pipeline by translating the testing world image back to the training domain when using the trained policy. In the translating process, a stochastic generator is used to generate various images stylized under the training domain randomly or directionally. Based on those translated images, the trained uncertainty-aware imitation learning policy would output both the predicted action and the data uncertainty motivated by the aleatoric loss function. Through the uncertainty-aware imitation learning policy, we can easily choose the safest one with the lowest uncertainty among the generated images. Experiments in the Carla navigation benchmark show that our strategy outperforms previous methods, especially in dynamic environments.

57.Keyframe-based Direct Thermal-Inertial Odometry pdf

This paper proposes an approach for fusing direct radiometric data from a thermal camera with inertial measurements to extend the robotic capabilities of aerial robots for navigation in GPS-denied and visually degraded environments in the conditions of darkness and in the presence of airborne obscurants such as dust, fog and smoke. An optimization based approach is developed that jointly minimizes the re-projection error of 3D landmarks and inertial measurement errors. The developed solution is extensively verified against both ground-truth in an indoor laboratory setting, as well as inside an underground mine under severely visually degraded conditions.

58.Marker based Thermal-Inertial Localization for Aerial Robots in Obscurant Filled Environments pdf

For robotic inspection tasks in known environments fiducial markers provide a reliable and low-cost solution for robot localization. However, detection of such markers relies on the quality of RGB camera data, which degrades significantly in the presence of visual obscurants such as fog and smoke. The ability to navigate known environments in the presence of obscurants can be critical for inspection tasks especially, in the aftermath of a disaster. Addressing such a scenario, this work proposes a method for the design of fiducial markers to be used with thermal cameras for the pose estimation of aerial robots. Our low cost markers are designed to work in the long wave infrared spectrum, which is not affected by the presence of obscurants, and can be affixed to any object that has measurable temperature difference with respect to its surroundings. Furthermore, the estimated pose from the fiducial markers is fused with inertial measurements in an extended Kalman filter to remove high frequency noise and error present in the fiducial pose estimates. The proposed markers and the pose estimation method are experimentally evaluated in an obscurant filled environment using an aerial robot carrying a thermal camera.

59.Time-Delay Momentum: A Regularization Perspective on the Convergence and Generalization of Stochastic Momentum for Deep Learning pdf

In this paper we study the problem of convergence and generalization error bound of stochastic momentum for deep learning from the perspective of regularization. To do so, we first interpret momentum as solving an $\ell_2$-regularized minimization problem to learn the offsets between arbitrary two successive model parameters. We call this {\em time-delay momentum} because the model parameter is updated after a few iterations towards finding the minimizer. We then propose our learning algorithm, \ie stochastic gradient descent (SGD) with time-delay momentum. We show that our algorithm can be interpreted as solving a sequence of strongly convex optimization problems using SGD. We prove that under mild conditions our algorithm can converge to a stationary point with rate of $O(\frac{1}{\sqrt{K}})$ and generalization error bound of $O(\frac{1}{\sqrt{n\delta}})$ with probability at least $1-\delta$, where $K,n$ are the numbers of model updates and training samples, respectively. We demonstrate the empirical superiority of our algorithm in deep learning in comparison with the state-of-the-art deep learning solvers.

60.Equilibrated Recurrent Neural Network: Neuronal Time-Delayed Self-Feedback Improves Accuracy and Stability pdf

We propose a novel {\it Equilibrated Recurrent Neural Network} (ERNN) to combat the issues of inaccuracy and instability in conventional RNNs. Drawing upon the concept of autapse in neuroscience, we propose augmenting an RNN with a time-delayed self-feedback loop. Our sole purpose is to modify the dynamics of each internal RNN state and, at any time, enforce it to evolve close to the equilibrium point associated with the input signal at that time. We show that such self-feedback helps stabilize the hidden state transitions leading to fast convergence during training while efficiently learning discriminative latent features that result in state-of-the-art results on several benchmark datasets at test-time. We propose a novel inexact Newton method to solve fixed-point conditions given model parameters for generating the latent features at each hidden state. We prove that our inexact Newton method converges locally with linear rate (under mild conditions). We leverage this result for efficient training of ERNNs based on backpropagation.

61.Strong homotopy of digitally continuous functions pdf

We introduce a new type of homotopy relation for digitally continuous functions which we call strong homotopy.&#39;&#39; Both digital homotopy and strong homotopy are natural digitizations of classical topological homotopy: the difference between them is analogous to the difference between digital 4-adjacency and 8-adjacency in the plane. <br />We explore basic properties of strong homotopy, and give some equivalent characterizations. In particular we show that strong homotopy is related to punctuated homotopy,'' in which the function changes by only one point in each homotopy time step.
We also show that strongly homotopic maps always have the same induced homomorphisms in the digital homology theory. This is not generally true for digitally homotopic maps, though we do show that it is true for any homotopic selfmaps on the digital cycle $C_n$ with $n\ge 4$.
We also define and consider strong homotopy equivalence of digital images. Using some computer assistance, we produce a catalog of all small digital images up to strong homotopy equivalence. We also briefly consider pointed strong homotopy equivalence, and give an example of a pointed contractible image which is not pointed strongly contractible.

62.PuVAE: A Variational Autoencoder to Purify Adversarial Examples pdf

Deep neural networks are widely used and exhibit excellent performance in many areas. However, they are vulnerable to adversarial attacks that compromise the network at the inference time by applying elaborately designed perturbation to input data. Although several defense methods have been proposed to address specific attacks, other attack methods can circumvent these defense mechanisms. Therefore, we propose Purifying Variational Autoencoder (PuVAE), a method to purify adversarial examples. The proposed method eliminates an adversarial perturbation by projecting an adversarial example on the manifold of each class, and determines the closest projection as a purified sample. We experimentally illustrate the robustness of PuVAE against various attack methods without any prior knowledge. In our experiments, the proposed method exhibits performances competitive with state-of-the-art defense methods, and the inference time is approximately 130 times faster than that of Defense-GAN that is the state-of-the art purifier model.

63.Sparse Depth Enhanced Direct Thermal-infrared SLAM Beyond the Visible Spectrum pdf

In this paper, we propose a thermal-infrared simultaneous localization and mapping (SLAM) system enhanced by sparse depth measurements from Light Detection and Ranging (LiDAR). Thermal-infrared cameras are relatively robust against fog, smoke, and dynamic lighting conditions compared to RGB cameras operating under the visible spectrum. Due to the advantages of thermal-infrared cameras, exploiting them for motion estimation and mapping is highly appealing. However, operating a thermal-infrared camera directly in existing vision-based methods is difficult because of the modality difference. This paper proposes a method to use sparse depth measurement for 6-DOF motion estimation by directly tracking under 14- bit raw measurement of the thermal camera. In addition, we perform a refinement to improve the local accuracy and include a loop closure to maintain global consistency. The experimental results demonstrate that the system is not only robust under various lighting conditions such as day and night, but also overcomes the scale problem of monocular cameras. The video is available at this https URL.