Attention Mechanisms
Channel Squeeze and Spatial Excitation (sSE)
Introduced by Roy et al. in Recalibrating Fully Convolutional Networks with Spatial and Channel 'Squeeze & Excitation' BlocksInspired on the widely known spatial squeeze and channel excitation (SE) block, the sSE block performs channel squeeze and spatial excitation, to recalibrate the feature maps spatially and achieve more fine-grained image segmentation.
Source: Recalibrating Fully Convolutional Networks with Spatial and Channel 'Squeeze & Excitation' Blocks
Papers
| Paper | Code | Results | Date | Stars |
|---|
Tasks
| Task | Papers | Share |
|---|---|---|
| Audio Classification | 1 | 14.29% |
| COVID-19 Diagnosis | 1 | 14.29% |
| Dimensionality Reduction | 1 | 14.29% |
| Environmental Sound Classification | 1 | 14.29% |
| Sound Classification | 1 | 14.29% |
| Image Classification | 1 | 14.29% |
| Semantic Segmentation | 1 | 14.29% |
Usage Over Time
Components
| Component | Type |
|
|---|---|---|
| 🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |
