pytorch-image-models icon indicating copy to clipboard operation
pytorch-image-models copied to clipboard
verified publisher icon huggingface

[FEATURE] FAN support

Open pfeatherstone opened this issue 3 years ago • 0 comments

Is your feature request related to a problem? Please describe. Models that are invariant under non-differentiable impairments like JPEG compression, video compression (H265, VP9, etc), etc.

Describe the solution you'd like This paper suggests they've solved this with ViT-like models and enhanced attention, called FAN

Describe alternatives you've considered Trained with differentiable approximations of non-differentiable impairments. Works a bit but not great.

pfeatherstone avatar May 03 '22 08:05 pfeatherstone