# Global Context Networks

arXiv: https://arxiv.org/abs/2012.13375 · HTML: https://mlsanity.com/paper/2012.13375/

## Key facts

- Cited by 35 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Dec 2020.

## Built on by (most cited first, 30 of 35)

- [Learning to Prompt for Open-Vocabulary Object Detection with Vision-Language Model](https://mlsanity.com/paper/2203.14940/) (2022)
- [Vision Transformers are Robust Learners](https://mlsanity.com/paper/2105.07581/) (2021)
- [Learning Enriched Features for Fast Image Restoration and Enhancement](https://mlsanity.com/paper/2205.01649/) (2022)
- [Conv2Former: A Simple Transformer-Style ConvNet for Visual Recognition](https://mlsanity.com/paper/2211.11943/) (2022)
- [CBNet: A Composite Backbone Network Architecture for Object Detection](https://mlsanity.com/paper/2107.00420/) (2021)
- [Towards Robust Rain Removal Against Adversarial Attacks: A Comprehensive Benchmark Analysis and Beyond](https://mlsanity.com/paper/2203.16931/) (2022)
- [Dual Vision Transformer](https://mlsanity.com/paper/2207.04976/) (2022)
- [NTIRE 2025 Challenge on Day and Night Raindrop Removal for Dual-Focused Images: Methods and Results](https://mlsanity.com/paper/2504.12711/) (2025)
- [Scratching Visual Transformer's Back with Uniform Attention](https://mlsanity.com/paper/2210.08457/) (2022)
- [Learning to Aggregate Multi-Scale Context for Instance Segmentation in Remote Sensing Images](https://mlsanity.com/paper/2111.11057/) (2021)
- [A Simple Single-Scale Vision Transformer for Object Localization and Instance Segmentation](https://mlsanity.com/paper/2112.09747/) (2021)
- [Unbiased Dynamic Multimodal Fusion](https://mlsanity.com/paper/2603.19681/) (2026)
- [A Multi-attribute Controllable Generative Model for Histopathology Image Synthesis](https://mlsanity.com/paper/2111.06398/) (2021)
- [Guided Context Gating: Learning to leverage salient lesions in retinal fundus images](https://mlsanity.com/paper/2406.13126/) (2024)
- [Exploring Resolution Fields for Scalable Image Compression with Uncertainty Guidance](https://mlsanity.com/paper/2306.08941/) (2023)
- [Investigating Neural Architectures by Synthetic Dataset Design](https://mlsanity.com/paper/2204.11045/) (2022)
- [Boosting Semantic Segmentation with Semantic Boundaries](https://mlsanity.com/paper/2304.09427/) (2023)
- [DocParseNet: Advanced Semantic Segmentation and OCR Embeddings for Efficient Scanned Document Annotation](https://mlsanity.com/paper/2406.17591/) (2024)
- [Dynamic Contextual Attention Network: Transforming Spatial Representations into Adaptive Insights for Endoscopic Polyp Diagnosis](https://mlsanity.com/paper/2504.20306/) (2025)
- [Efficient Generative Transformer Operators For Million-Point PDEs](https://mlsanity.com/paper/2512.04974/) (2025)
- [Benchmarking Semantic Segmentation Models via Appearance and Geometry Attribute Editing](https://mlsanity.com/paper/2603.01535/) (2026)
- [Teaching with Uncertainty: Unleashing the Potential of Knowledge Distillation in Object Detection](https://mlsanity.com/paper/2406.06999/) (2024)
- [Global Context Modeling in YOLOv8 for Pediatric Wrist Fracture Detection](https://mlsanity.com/paper/2407.03163/) (2024)
- [Pediatric Wrist Fracture Detection Using Feature Context Excitation Modules in X-ray Images](https://mlsanity.com/paper/2410.01031/) (2024)
- [BlurBall: Joint Ball and Motion Blur Estimation for Table Tennis Ball Tracking](https://mlsanity.com/paper/2509.18387/) (2025)
- [LIGAR: Lightweight General-purpose Action Recognition](https://mlsanity.com/paper/2108.13153/) (2021)
- [Anatomically aware dual-hop learning for pulmonary embolism detection in CT pulmonary angiograms](https://mlsanity.com/paper/2303.17593/) (2023)
- [Enhancing Vehicle Make and Model Recognition with 3D Attention Modules](https://mlsanity.com/paper/2502.15398/) (2025)
- [Convolutional Rectangular Attention Module](https://mlsanity.com/paper/2503.10875/) (2025)
- [Few-Shot Object Detection via Spatial-Channel State Space Model](https://mlsanity.com/paper/2507.15308/) (2025)

## Abstract (arXiv)

The Non-Local Network (NLNet) presents a pioneering approach for capturing long-range dependencies within an image, via aggregating query-specific global context to each query position. However, through a rigorous empirical analysis, we have found that the global contexts modeled by the non-local network are almost the same for different query positions. In this paper, we take advantage of this finding to create a simplified network based on a query-independent formulation, which maintains the accuracy of NLNet but with significantly less computation. We further replace the one-layer transformation function of the non-local block by a two-layer bottleneck, which further reduces the parameter number considerably. The resulting network element, called the global context (GC) block, effectively models global context in a lightweight manner, allowing it to be applied at multiple layers of a backbone network to form a global context network (GCNet). Experiments show that GCNet generally outperforms NLNet on major benchmarks for various recognition tasks. The code and network configurations are available at https://github.com/xvjiarui/GCNet.