Inspired 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' BlocksPaper | Code | Results | Date | Stars |
---|
Task | Papers | Share |
---|---|---|
Audio Classification | 1 | 12.50% |
COVID-19 Diagnosis | 1 | 12.50% |
Dimensionality Reduction | 1 | 12.50% |
Environmental Sound Classification | 1 | 12.50% |
Sound Classification | 1 | 12.50% |
Decoder | 1 | 12.50% |
Image Classification | 1 | 12.50% |
Semantic Segmentation | 1 | 12.50% |
Component | Type |
|
---|---|---|
🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |