# Variations of Squeeze and Excitation networks

arXiv: https://arxiv.org/abs/2304.06502 · HTML: https://mlsanity.com/paper/2304.06502/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 16 of its 18 references that are in the map.
- First posted on arXiv 11 Apr 2023.

## Builds on (most cited first, 16 of 16)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [Going Deeper with Convolutions](https://mlsanity.com/paper/1409.4842/) (2014)
- [MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications](https://mlsanity.com/paper/1704.04861/) (2017)
- [A ConvNet for the 2020s](https://mlsanity.com/paper/2201.03545/) (2022)
- [Wide Residual Networks](https://mlsanity.com/paper/1605.07146/) (2016)
- [Aggregated Residual Transformations for Deep Neural Networks](https://mlsanity.com/paper/1611.05431/) (2016)
- [Xception: Deep Learning with Depthwise Separable Convolutions](https://mlsanity.com/paper/1610.02357/) (2016)
- [Searching for MobileNetV3](https://mlsanity.com/paper/1905.02244/) (2019)
- [EfficientNetV2: Smaller Models and Faster Training](https://mlsanity.com/paper/2104.00298/) (2021)
- [Network In Network](https://mlsanity.com/paper/1312.4400/) (2013)
- [DropBlock: A regularization method for convolutional networks](https://mlsanity.com/paper/1810.12890/) (2018)
- [Training Very Deep Networks](https://mlsanity.com/paper/1507.06228/) (2015)
- [An Enhanced Hybrid MobileNet](https://mlsanity.com/paper/1712.04698/) (2017)

## Abstract (arXiv)

Convolutional neural networks learns spatial features and are heavily interlinked within kernels. The SE module have broken the traditional route of neural networks passing the entire result to next layer. Instead SE only passes important features to be learned with its squeeze and excitation (SE) module. We propose variations of the SE module which improvises the process of squeeze and excitation and enhances the performance. The proposed squeezing or exciting the layer makes it possible for having a smooth transition of layer weights. These proposed variations also retain the characteristics of SE module. The experimented results are carried out on residual networks and the results are tabulated.