search

blackfeather-wang / ISDA-for-Deep-Networks

An efficient implicit semantic augmentation method, complementary to existing non-semantic techniques.
582 stars 93 forks source link

Questions about ISDA for ImageNet #32

Closed JamenceTom closed 1 year ago

JamenceTom commented 2 years ago

Thank you for your great work!!! Sorry to bother you, I am confused on the implementation of ISDA for ImageNet, as shown in the following image. image Why do you only consider the diagonal elements of sigma2?

jackliu333 commented 2 years ago

It could be this implementation ignores the covariance between deep features.

blackfeather-wang commented 1 year ago

Indeed, we ignore the covariance between deep features on ImageNet (only ImageNet) to save the GPU memory. Take ResNet-50 for example. If we consider all the covariance, we will have a 1000 2048 2048 tensor, while in the current implementation, we only need to process a 1000 * 2048 tensor. We find that ISDA significantly improves the accuracy even with this implementation technique.