# Region Aware Squeeze-and-Excitation Networks for Image Segmentation

arXiv: https://arxiv.org/abs/2610.15079 · HTML: https://mlsanity.com/paper/2610.15079/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 23 of its 36 references that are in the map.
- First posted on arXiv 10 Oct 2026.

## Builds on (most cited first, 23 of 23)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [Fully Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1411.4038/) (2014)
- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [CBAM: Convolutional Block Attention Module](https://mlsanity.com/paper/1807.06521/) (2018)
- [Matching Networks for One Shot Learning](https://mlsanity.com/paper/1606.04080/) (2016)
- [ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networks](https://mlsanity.com/paper/1910.03151/) (2019)
- [Coordinate Attention for Efficient Mobile Network Design](https://mlsanity.com/paper/2103.02907/) (2021)
- [FcaNet: Frequency Channel Attention Networks](https://mlsanity.com/paper/2012.11879/) (2020)
- [Gather-Excite: Exploiting Feature Context in Convolutional Neural Networks](https://mlsanity.com/paper/1810.12348/) (2018)
- [Concurrent Spatial and Channel Squeeze & Excitation in Fully Convolutional Networks](https://mlsanity.com/paper/1803.02579/) (2018)
- [Recalibrating Fully Convolutional Networks with Spatial and Channel 'Squeeze & Excitation' Blocks](https://mlsanity.com/paper/1808.08127/) (2018)
- [SRM : A Style-based Recalibration Module for Convolutional Neural Networks](https://mlsanity.com/paper/1903.10829/) (2019)
- [Squeeze-and-Attention Networks for Semantic Segmentation](https://mlsanity.com/paper/1909.03402/) (2019)
- [Gated Channel Transformation for Visual Recognition](https://mlsanity.com/paper/1909.11519/) (2019)
- [Efficient Multi-Scale Attention Module with Cross-Spatial Learning](https://mlsanity.com/paper/2305.13563/) (2023)
- [SCSA: Exploring the Synergistic Effects Between Spatial and Channel Attention](https://mlsanity.com/paper/2407.05128/) (2024)
- [Recalibrating 3D ConvNets with Project & Excite](https://mlsanity.com/paper/2002.10994/) (2020)
- [Efficient semantic image segmentation with superpixel pooling](https://mlsanity.com/paper/1806.02705/) (2018)
- [Tiled Squeeze-and-Excite: Channel Attention With Local Spatial Context](https://mlsanity.com/paper/2107.02145/) (2021)
- [MCA: Moment Channel Attention Networks](https://mlsanity.com/paper/2403.01713/) (2024)

## Abstract (arXiv)

Squeeze-and-Excitation (SE) modules improve convolutional networks by modeling channel-wise dependencies, but global average pooling collapses spatial structure into a single per-channel descriptor, limiting their effectiveness for dense prediction tasks such as image segmentation. We generalize SE by replacing global pooling with spatially guided pooling, enabling region-aware channel recalibration through four modules with complementary cost profiles. BASE formalizes Tiled Squeeze-and-Excite using a regular grid; SPASE pools over SLIC superpixels for image-adaptive regions; MAPSE obtains regions from semantic maps produced by a frozen, general-purpose network; and PLEASE learns soft region assignments end-to-end through a lightweight assignment network. Each channel receives one gate per region, so attention at each pixel reflects its region membership, bridging channel and spatial attention. PLEASE also produces its soft assignments as a byproduct of the forward pass, providing structured spatial interpretability without post-hoc analysis. The modules offer complementary computational tradeoffs: some add essentially no parameters, while others add no measurable latency. Across binary segmentation on CUB, DUTS, and ECSSD, semantic segmentation on PASCAL VOC 2012 and ADE20K, and classification on mini-ImageNet, our modules outperform SE and related spatial-channel attention variants on most benchmarks, achieving the majority of best results.