Lin Zhang
Lin Zhang
Hi, Thank you for the awesome work! Can you provide the source pretrained model or any command to reproduce your result in Table 4 row 1 (w/o target source train)...
Hi, the paper mentioned lower FID score, but I can not find the calculation/network structure of FID. May I know which layer of I3D did you use for calculating FID?
Hi, I realized that you have used the wrong implementation of DANN(revgrad). Specifically, you attach the discriminator after the classifier instead of the penultimate layer. see here: https://github.com/virajprabhu/CLUE/blob/99cb2b498fe42ab8ba8425eebb021e8fba7ec960/adapt/models/adapt_net.py#L49 But in...
Thank you for the fantastic work! I realized that the "ndomain" parameter in config is always set to 2, which should be the target-combined setting in your paper. May I...