The Squeeze-and-Excitation Block is an architectural unit designed to improve the representational power of a network by enabling it to perform dynamic channel-wise feature recalibration. The process is:
Paper | Code | Results | Date | Stars |
---|
Task | Papers | Share |
---|---|---|
Image Classification | 88 | 16.30% |
Object Detection | 45 | 8.33% |
Semantic Segmentation | 30 | 5.56% |
General Classification | 29 | 5.37% |
Classification | 22 | 4.07% |
Instance Segmentation | 15 | 2.78% |
Multi-Task Learning | 9 | 1.67% |
Quantization | 8 | 1.48% |
Emotion Recognition | 7 | 1.30% |
Component | Type |
|
---|---|---|
![]() |
Pooling Operations | |
![]() |
Convolutions | |
![]() |
Feedforward Networks | |
![]() |
Activation Functions | |
![]() |
Activation Functions |