Implementing CMC on CIFAR-10

[hobbitlong]

Implementing CMC on CIFAR-10

[ShaoTengLiu]

Update. I think this may be caused by #27. I find there seems no method to prevent an element in the enqueue come from the same sample as the query. As a result, the loss increases a lot at the beginning of each epoch.

This may not hurt performance when the dataset is large enough. However, for CIFAR-10, which only consists of 50,000 samples, this may hurt the performance a lot.

[ShaoTengLiu]

Update. I find you gave some hint on this problem, as shown in hint. Can I conclude that we should use softmax and less negative samples to implement CMC on small datasets?

[HobbitLong]

@ShaoTengLiu ,

Sorry for the late reply, I have obtained ~70% on CIFAR100. I think using 2048 might suffice on CIFAR datasets (10 or 100). Also you could sample without replacement to solve the conflict issue you just pointed to.

[ShaoTengLiu]

@HobbitLong ,

Thanks for your reply. Yes, 2048 or 4096 is suffice on CIFAR. The problem has been solved. You can close this issue. Thank you very much.

[HobbitLong]

Glad that you have figured it out. Feel free to reopen for future issues!

[WeihongM]

@HobbitLong ,

Thanks for your reply. Yes, 2048 or 4096 is suffice on CIFAR. The problem has been solved. You can close this issue. Thank you very much.

Hello， @ShaoTengLiu
Can you share the performance you reach when using cifar-10 dataset.