Image Model Blocks

Squeeze-and-Excitation Block

Introduced by Hu et al. in Squeeze-and-Excitation Networks

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:

  • The block has a convolutional block as an input.
  • Each channel is "squeezed" into a single numeric value using average pooling.
  • A dense layer followed by a ReLU adds non-linearity and output channel complexity is reduced by a ratio.
  • Another dense layer followed by a sigmoid gives each channel a smooth gating function.
  • Finally, we weight each feature map of the convolutional block based on the side network; the "excitation".
Source: Squeeze-and-Excitation Networks


Paper Code Results Date Stars


Task Papers Share
Image Classification 101 14.41%
Object Detection 49 6.99%
Semantic Segmentation 37 5.28%
Classification 34 4.85%
General Classification 29 4.14%
Instance Segmentation 16 2.28%
Test 14 2.00%
Quantization 11 1.57%
Multi-Task Learning 10 1.43%