# Spatial Group-wise Enhance: Improving Semantic Feature Learning in Convolutional Networks

arXiv: https://arxiv.org/abs/1905.09646 · HTML: https://mlsanity.com/paper/1905.09646/

## Key facts

- Cited by 33 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 May 2019.

## Built on by (most cited first, 30 of 33)

- [Distract Your Attention: Multi-head Cross Attention Network for Facial Expression Recognition](https://mlsanity.com/paper/2109.07270/) (2021)
- [SA-Net: Shuffle Attention for Deep Convolutional Neural Networks](https://mlsanity.com/paper/2102.00240/) (2021)
- [Intensity-Aware Loss for Dynamic Facial Expression Recognition in the Wild](https://mlsanity.com/paper/2208.10335/) (2022)
- [Efficient Multi-Scale Attention Module with Cross-Spatial Learning](https://mlsanity.com/paper/2305.13563/) (2023)
- [Spectral Unsupervised Domain Adaptation for Visual Recognition](https://mlsanity.com/paper/2106.06112/) (2021)
- [DA-DETR: Domain Adaptive Detection Transformer with Information Fusion](https://mlsanity.com/paper/2103.17084/) (2021)
- [Salient Object Detection in Optical Remote Sensing Images Driven by Transformer](https://mlsanity.com/paper/2309.08206/) (2023)
- [BA-Net: Bridge Attention for Deep Convolutional Neural Networks](https://mlsanity.com/paper/2112.04150/) (2021)
- [Understanding Self-attention Mechanism via Dynamical System Perspective](https://mlsanity.com/paper/2308.09939/) (2023)
- [ELA: Efficient Local Attention for Deep Convolutional Neural Networks](https://mlsanity.com/paper/2403.01123/) (2024)
- [The Lottery Ticket Hypothesis for Self-attention in Convolutional Neural Network](https://mlsanity.com/paper/2207.07858/) (2022)
- [AFter: Attention-based Fusion Router for RGBT Tracking](https://mlsanity.com/paper/2405.02717/) (2024)
- [BA^2M: A Batch Aware Attention Module for Image Classification](https://mlsanity.com/paper/2103.15099/) (2021)
- [Poly-NL: Linear Complexity Non-local Layers with Polynomials](https://mlsanity.com/paper/2107.02859/) (2021)
- [A Generic Shared Attention Mechanism for Various Backbone Neural Networks](https://mlsanity.com/paper/2210.16101/) (2022)
- [Spatial-information Guided Adaptive Context-aware Network for Efficient RGB-D Semantic Segmentation](https://mlsanity.com/paper/2308.06024/) (2023)
- [Mix-Pooling Strategy for Attention Mechanism](https://mlsanity.com/paper/2208.10322/) (2022)
- [Attention-guided Feature Distillation for Semantic Segmentation](https://mlsanity.com/paper/2403.05451/) (2024)
- [CAT: Learning to Collaborate Channel and Spatial Attention from Multi-Information Fusion](https://mlsanity.com/paper/2212.06335/) (2022)
- [ASR: Attention-alike Structural Re-parameterization](https://mlsanity.com/paper/2304.06345/) (2023)
- [MRC-DETR: An Adaptive Multi-Residual Coupled Transformer for Bare Board PCB Defect Detection](https://mlsanity.com/paper/2507.03386/) (2025)
- [Semantic Embedded Deep Neural Network: A Generic Approach to Boost Multi-Label Image Classification Performance](https://mlsanity.com/paper/2305.05228/) (2023)
- [Fast One-Stage Unsupervised Domain Adaptive Person Search](https://mlsanity.com/paper/2405.02832/) (2024)
- [CSANet: Channel Spatial Attention Network for Robust 3D Face Alignment and Reconstruction](https://mlsanity.com/paper/2405.19659/) (2024)
- [YO-CSA-T: A Real-time Badminton Tracking System Utilizing YOLO Based on Contextual and Spatial Attention](https://mlsanity.com/paper/2501.06472/) (2025)
- [Breaking Alignment Barriers: TPS-Driven Semantic Correlation Learning for Alignment-Free RGB-T Salient Object Detection](https://mlsanity.com/paper/2512.21856/) (2025)
- [Rega-Net:Retina Gabor Attention for Deep Convolutional Neural Networks](https://mlsanity.com/paper/2211.12698/) (2022)
- [Application of attention-based Siamese composite neural network in medical image recognition](https://mlsanity.com/paper/2304.09783/) (2023)
- [CBAGAN-RRT: Convolutional Block Attention Generative Adversarial Network for Sampling-Based Path Planning](https://mlsanity.com/paper/2305.10442/) (2023)
- [A Time-Enhanced Data Disentanglement Network for Traffic Flow Forecasting](https://mlsanity.com/paper/2506.02609/) (2025)

## Abstract (arXiv)

The Convolutional Neural Networks (CNNs) generate the feature representation of complex objects by collecting hierarchical and different parts of semantic sub-features. These sub-features can usually be distributed in grouped form in the feature vector of each layer, representing various semantic entities. However, the activation of these sub-features is often spatially affected by similar patterns and noisy backgrounds, resulting in erroneous localization and identification. We propose a Spatial Group-wise Enhance (SGE) module that can adjust the importance of each sub-feature by generating an attention factor for each spatial location in each semantic group, so that every individual group can autonomously enhance its learnt expression and suppress possible noise. The attention factors are only guided by the similarities between the global and local feature descriptors inside each group, thus the design of SGE module is extremely lightweight with almost no extra parameters and calculations. Despite being trained with only category supervisions, the SGE component is extremely effective in highlighting multiple active areas with various high-order semantics (such as the dog's eyes, nose, etc.). When integrated with popular CNN backbones, SGE can significantly boost the performance of image recognition tasks. Specifically, based on ResNet50 backbones, SGE achieves 1.2% Top-1 accuracy improvement on the ImageNet benchmark and 1.0~2.0% AP gain on the COCO benchmark across a wide range of detectors (Faster/Mask/Cascade RCNN and RetinaNet). Codes and pretrained models are available at https://github.com/implus/PytorchInsight.