pcmepp
pcmepp copied to clipboard
Official Pytorch implementation of "Improved Probabilistic Image-Text Representations" (ICLR 2024)
 Hello! While studying your code, I found that when resampling is used here, it seems to be calculated directly using the variance. In my understanding, resampling seems to be...
 For binary loss, the final derivative results seem to be different from the paper, when m=0 or 1, I calculated the results as -sigmoid(l_vt) and sigmoid(-l_vt), respectively.