Stand-Alone Self Attention (SASA) replaces all instances of spatial convolution with a form of self-attention applied to ResNet producing a fully, stand-alone self-attentional model.
Source: Stand-Alone Self-Attention in Vision ModelsPaper | Code | Results | Date | Stars |
---|
Task | Papers | Share |
---|---|---|
Object Detection | 2 | 33.33% |
3D Object Detection | 1 | 16.67% |
Face Anti-Spoofing | 1 | 16.67% |
Face Recognition | 1 | 16.67% |
Style Transfer | 1 | 16.67% |
Component | Type |
|
---|---|---|
🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |