Harsh Rangwani

icon indicating a website link https://rangwani-harsh.github.io/ icon indicating an email [email protected]

icon company Indian Institute of Science icon location Bengaluru icon location @val-iisc

Results 4 comments of Harsh Rangwani

[CVPR 2023] Adding NoisyTwins Regularization to StyleGAN2

We will submit the pull request with the required code changes in case you all agree for it to be integrated in StudioGAN.

Different behaviours on VisDA-2017 using different pretrained models from timm

Hi @swift-n-brutal are you now able to get the correct accuracy for VisDA dataset?

Unavailable dataset

Hi, I have updated the office-home dataset links, can you pull the latest changes from the library and check again?

about domain acc

Thanks for your interest in our work. We suggest you start with domain adaptive image regression work (like https://arxiv.org/pdf/2006.08251.pdf) and then apply SDAT to observe improvement. (see our README.MD on...