CAGAM is a form of spatial attention mechanism that propagates attention from a known to an unknown context features thereby enhancing the unknown context for relevant pattern discovery. Usually the known context feature is a class activation map (CAM).
Source: Rendezvous: Attention Mechanisms for the Recognition of Surgical Action Triplets in Endoscopic VideosPaper | Code | Results | Date | Stars |
---|
Task | Papers | Share |
---|---|---|
Out-of-Distribution Detection | 1 | 33.33% |
Out of Distribution (OOD) Detection | 1 | 33.33% |
Action Triplet Recognition | 1 | 33.33% |
Component | Type |
|
---|---|---|
🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |