Have you tried 90 epochs training with mixup on ImageNet or iNaturalist ?

[liming-ai]

Hi @zs-zhong ,

Have you tried 90 epochs training with mixup on ImageNet or iNaturalist ?

I have made some improvements based on your work, but due to the lack of computing resources, training a model for 180/200 epochs is too time-consuming for me, especially for iNaturalist.

In my reproduction, under the condition of training 90 epochs with mixup (alpha 0.2) on ImageNet-LT, epochs of stage-2 is 10, the accuracy of methods with ResNet-50 are as follows:

	Stage-1	mixup	Stage-2	cRT	LWS
Reported in Decouple	90 epochs		10 epochs	47.3	47.7
My Reproduce	90 epochs		10 epochs	48.7	49.3
My Reproduce	90 epochs	✅	10 epochs	47.6	47.4
My Reproduce	180 epochs		10 epochs	51.0	51.8
Reported in MiSLAS	180 epochs		10 epochs	50.3	51.2
Reported in MiSLAS	180 epochs	✅	10 epochs	51.7	52.0

They look much worse than the model trained for 180 epochs with mixup, and it does not even have improvement compared to normal training.

I guess this is because mixup could be regarded as a regularization method, which requires longer training epochs, 90 epochs cannot make the network converge.

However, I cannot get the result of using mixup to train 90 epochs on the iNaturalist data set, because the iNaturalist data set is too large and I can't put it in the memory, which makes it take about a week for me to train R50 once.

If possible, could you please provide the pre-trained ResNet-50 model for training 90 epochs with mixup on iNaturalist? I believe this will also be beneficial for fair comparison of future work.

Thank you again for your contribution and look forward to your reply.

[zs-zhong]

Hi, I agree that mixup could be regarded as a regularization method and requires longer training epochs to make the training process converge.
We are so sorry that we don't have the model that trained for 90 epochs with mixup on iNaturalist now.
We are very busy recently and could you please wait for one or two months? Sorry again!

[liming-ai]

Hi, I agree that mixup could be regarded as a regularization method and requires longer training epochs to make the training process converge. We are so sorry that we don't have the model that trained for 90 epochs with mixup on iNaturalist now. We are very busy recently and could you please wait for one or two months? Sorry again!

Of course, thanks for your reply, best wishes to your CVPR submission