alexandonian/contrastive-feature-loss

PyTorch implementation of Contrastive Feature Loss for Image Prediction (AIM Workshop at ICCV 2021)

contrastive-feature-loss's Issues

The meaning of "nce_fake_negatives" argument

Hi, Thank you very much for sharing the code. Could you please explain the meaning of "nce_fake_negatives"? I didn't find any corresponding description of this in the paper.

Read Me Typo

"Contrastive Feature Loss for Image Predcition"

Problem about the NCE convergence curve

Hi, we just adopt the official setting of contrastive feature loss, and obtain the NCE convergence curve as:

which is significant different to NCE curve in the paper, can you provide more training details/settings to help us find the problem? Thanks~

Problem about the stop gradient operation for negative pairs.

According to the equation (5) in paper, which says that "gradients are prevented from flowing through the negatives". Then for the PatchNCELoss function in

contrastive-feature-loss/models/networks/nce.py

Line 30 in 788ac92

if not self.opt.gradient_flows_to_negative_nce:

, should we detach feat_k after the calculation of pos logits?