sundw2014/dks

Deeply-supervised Knowledge Synergy (CVPR'2019)

dks's Issues

about the data

hi,
Thanks for sharing your code.I'd like to ask you about the data if I want to use the data of "224*224", how can I modify the network?

Supplementary material of DKS

@sundw2014 Thanks for sharing the codes. Inspired by your awesome work, I wonder if you can share your supplementary material with me since I am very interested in the theoretical analysis of DKS. Thanks a lot.

Question about the knowledge matching strategies

Hi I have a small question about the various knowledge matching strategies.

In the experiment, bottom-up strategy is way better than top-down one, and why do you think so?
In my knowledge, upper layer may predict more precise logits, which can be more beneficial to guide lower layers to mimic precise logits, so that can lead to top-down strategy surpass bottom-up.

By the way, thanks for providing such a wonderful work! Im very impressed from your research.