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 | 105 | 13.69% |
Object Detection | 48 | 6.26% |
Semantic Segmentation | 38 | 4.95% |
Classification | 37 | 4.82% |
General Classification | 29 | 3.78% |
Instance Segmentation | 17 | 2.22% |
Decoder | 16 | 2.09% |
Quantization | 13 | 1.69% |
Multi-Task Learning | 10 | 1.30% |
Component | Type |
|
---|---|---|
Average Pooling
|
Pooling Operations | |
Convolution
|
Convolutions | |
Dense Connections
|
Feedforward Networks | |
ReLU
|
Activation Functions | |
Sigmoid Activation
|
Activation Functions |