# Compact Generalized Non-local Network

arXiv: https://arxiv.org/abs/1810.13125 · HTML: https://mlsanity.com/paper/1810.13125/

## Key facts

- Cited by 36 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 31 Oct 2018.

## Built on by (most cited first, 30 of 36)

- [Dynamic Neural Networks: A Survey](https://mlsanity.com/paper/2102.04906/) (2021)
- [Attention Mechanisms in Computer Vision: A Survey](https://mlsanity.com/paper/2111.07624/) (2021)
- [Involution: Inverting the Inherence of Convolution for Visual Recognition](https://mlsanity.com/paper/2103.06255/) (2021)
- [TSA-Net: Tube Self-Attention Network for Action Quality Assessment](https://mlsanity.com/paper/2201.03746/) (2022)
- [Learning Semantic Correspondence with Sparse Annotations](https://mlsanity.com/paper/2208.06974/) (2022)
- [Aligning Correlation Information for Domain Adaptation in Action Recognition](https://mlsanity.com/paper/2107.04932/) (2021)
- [DSANet: Dynamic Segment Aggregation Network for Video-Level Representation Learning](https://mlsanity.com/paper/2105.12085/) (2021)
- [TFCNet: Temporal Fully Connected Networks for Static Unbiased Temporal Reasoning](https://mlsanity.com/paper/2203.05928/) (2022)
- [Temporal-attentive Covariance Pooling Networks for Video Recognition](https://mlsanity.com/paper/2110.14381/) (2021)
- [CrossFormer: Cross Spatio-Temporal Transformer for 3D Human Pose Estimation](https://mlsanity.com/paper/2203.13387/) (2022)
- [Hyper-Convolution Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/2105.10559/) (2021)
- [SFNet: Faster and Accurate Semantic Segmentation via Semantic Flow](https://mlsanity.com/paper/2207.04415/) (2022)
- [Image Compressed Sensing Using Non-local Neural Network](https://mlsanity.com/paper/2112.03712/) (2021)
- [Global Aggregation then Local Distribution for Scene Parsing](https://mlsanity.com/paper/2107.13154/) (2021)
- [Fine-Grained Visual Classification using Self Assessment Classifier](https://mlsanity.com/paper/2205.10529/) (2022)
- [Poly-NL: Linear Complexity Non-local Layers with Polynomials](https://mlsanity.com/paper/2107.02859/) (2021)
- [Enhancing Local Feature Learning for 3D Point Cloud Processing using Unary-Pairwise Attention](https://mlsanity.com/paper/2203.00172/) (2022)
- [ViGAT: Bottom-up event recognition and explanation in video using factorized graph attention network](https://mlsanity.com/paper/2207.09927/) (2022)
- [Unifying Nonlocal Blocks for Neural Networks](https://mlsanity.com/paper/2108.02451/) (2021)
- [LSSANet: A Long Short Slice-Aware Network for Pulmonary Nodule Detection](https://mlsanity.com/paper/2208.02122/) (2022)
- [Zero-Shot Semantic Segmentation via Spatial and Multi-Scale Aware Visual Class Embedding](https://mlsanity.com/paper/2111.15181/) (2021)
- [Action Keypoint Network for Efficient Video Recognition](https://mlsanity.com/paper/2201.06304/) (2022)
- [Hyper-Convolutions via Implicit Kernels for Medical Imaging](https://mlsanity.com/paper/2202.02701/) (2022)
- [UGCANet: A Unified Global Context-Aware Transformer-based Network with Feature Alignment for Endoscopic Image Analysis](https://mlsanity.com/paper/2307.06260/) (2023)
- [Breaking the Resource Wall: Geometry-Guided Sequence Modeling for Efficient Semantic Segmentation](https://mlsanity.com/paper/2604.23399/) (2026)
- [Efficient Spatialtemporal Context Modeling for Action Recognition](https://mlsanity.com/paper/2103.11190/) (2021)
- [Efficient Transfer Learning via Joint Adaptation of Network Architecture and Weight](https://mlsanity.com/paper/2105.08994/) (2021)
- [Conviformers: Convolutionally guided Vision Transformer](https://mlsanity.com/paper/2208.08900/) (2022)
- [Gated-ViGAT: Efficient Bottom-Up Event Recognition and Explanation Using a New Frame Selection Policy and Gating Mechanism](https://mlsanity.com/paper/2301.07565/) (2023)
- [GeoDeformer: Geometric Deformable Transformer for Action Recognition](https://mlsanity.com/paper/2311.17975/) (2023)

## Abstract (arXiv)

The non-local module is designed for capturing long-range spatio-temporal dependencies in images and videos. Although having shown excellent performance, it lacks the mechanism to model the interactions between positions across channels, which are of vital importance in recognizing fine-grained objects and actions. To address this limitation, we generalize the non-local module and take the correlations between the positions of any two channels into account. This extension utilizes the compact representation for multiple kernel functions with Taylor expansion that makes the generalized non-local module in a fast and low-complexity computation flow. Moreover, we implement our generalized non-local method within channel groups to ease the optimization. Experimental results illustrate the clear-cut improvements and practical applicability of the generalized non-local module on both fine-grained object recognition and video classification. Code is available at: https://github.com/KaiyuYue/cgnl-network.pytorch.