Attention Mechanisms
Channel-wise Soft Attention
Channel-wise Soft Attention is an attention mechanism in computer vision that assigns "soft" attention weights for each channel $c$. In soft channel-wise attention, the alignment weights are learned and placed "softly" over each channel. This would contrast with hard attention which would only selects one channel to attend to at a time.
Image: Xu et al
Papers
| Paper | Code | Results | Date | Stars |
|---|
Tasks
| Task | Papers | Share |
|---|---|---|
| Image Classification | 6 | 10.53% |
| Semantic Segmentation | 5 | 8.77% |
| Object Detection | 4 | 7.02% |
| Instance Segmentation | 4 | 7.02% |
| Point Cloud Completion | 2 | 3.51% |
| Fake News Detection | 1 | 1.75% |
| 3D Classification | 1 | 1.75% |
| Classification | 1 | 1.75% |
| Object Detection In Aerial Images | 1 | 1.75% |
Usage Over Time
Components
| Component | Type |
|
|---|---|---|
| 🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |
