exponential-moving-average-normalization icon indicating copy to clipboard operation
exponential-moving-average-normalization copied to clipboard

PyTorch implementation of EMAN for self-supervised and semi-supervised learning: https://arxiv.org/abs/2101.08482

Results 2 exponential-moving-average-normalization issues
Sort by recently updated
recently updated
newest added

Hi, Thank you for uploading the code. I understand that EMAM is implemented in `momentum_update(self, cur_iter, max_iter)` method of `BYOLEMAM class`. Since minibatch mean (mu) and variance(sigma^2) are not trainable...

Hi, I have a question for the experimental setup in Table 7 of the paper (i.e., The comparison with other semi-supervised models.) What are the experimental settings used when compared...