Skip to content

Focal Loss implementation for multi class classification problem.

License

Notifications You must be signed in to change notification settings

SanketAgrawal/Catagorical-Focal-Loss

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

4 Commits
 
 
 
 
 
 
 
 

Repository files navigation

Catagorical-Focal-Loss

Focal Loss implementation for multi class classification problem. Citation: arXiv:1708.02002 [cs.CV] Paper Link: https://arxiv.org/abs/1708.02002

The highest accuracy object detectors to date are based on a two-stage approach popularized by R-CNN, where a classifier is applied to a sparse set of candidate object locations. In contrast, one-stage detectors that are applied over a regular, dense sampling of possible object locations have the potential to be faster and simpler, but have trailed the accuracy of two-stage detectors thus far. In this paper, we investigate why this is the case. We discover that the ex- treme foreground-background class imbalance encountered during training of dense detectors is the central cause. We propose to address this class imbalance by reshaping the standard cross entropy loss such that it down-weights the loss assigned to well-classified examples. Our novel Focal Loss focuses training on a sparse set of hard examples and prevents the vast number of easy negatives from overwhelming the detector during training. To evaluate the effective- ness of our loss, we design and train a simple dense detector we call RetinaNet. Our results show that when trained with the focal loss, RetinaNet is able to match the speed of previous one-stage detectors while surpassing the accuracy of all existing state-of-the-art two-stage detectors.

About

Focal Loss implementation for multi class classification problem.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published