# Context-Gated Convolution

arXiv: https://arxiv.org/abs/1910.05577 · HTML: https://mlsanity.com/paper/1910.05577/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Oct 2019.

## Built on by (most cited first, 23 of 23)

- [Perceiver: General Perception with Iterative Attention](https://mlsanity.com/paper/2103.03206/) (2021)
- [Omni-Dimensional Dynamic Convolution](https://mlsanity.com/paper/2209.07947/) (2022)
- [Adaptive Dynamic Filtering Network for Image Denoising](https://mlsanity.com/paper/2211.12051/) (2022)
- [Frequency Dynamic Convolution for Dense Image Prediction](https://mlsanity.com/paper/2503.18783/) (2025)
- [Mutual Information-driven Triple Interaction Network for Efficient Image Dehazing](https://mlsanity.com/paper/2308.06998/) (2023)
- [Cross-receptive Focused Inference Network for Lightweight Image Super-Resolution](https://mlsanity.com/paper/2207.02796/) (2022)
- [RefConv: Re-parameterized Refocusing Convolution for Powerful ConvNets](https://mlsanity.com/paper/2310.10563/) (2023)
- [Optical Flow Reusing for High-Efficiency Space-Time Video Super Resolution](https://mlsanity.com/paper/2110.06786/) (2021)
- [Video Event Extraction via Tracking Visual States of Arguments](https://mlsanity.com/paper/2211.01781/) (2022)
- [Fast and High-Quality Image Denoising via Malleable Convolutions](https://mlsanity.com/paper/2201.00392/) (2022)
- [KernelWarehouse: Rethinking the Design of Dynamic Convolution](https://mlsanity.com/paper/2406.07879/) (2024)
- [KernelWarehouse: Towards Parameter-Efficient Dynamic Convolution](https://mlsanity.com/paper/2308.08361/) (2023)
- [Audio Anti-spoofing Using a Simple Attention Module and Joint Optimization Based on Additive Angular Margin Loss and Meta-learning](https://mlsanity.com/paper/2211.09898/) (2022)
- [3D Human Pose Lifting with Grid Convolution](https://mlsanity.com/paper/2302.08760/) (2023)
- [NOAH: Learning Pairwise Object Category Attentions for Image Classification](https://mlsanity.com/paper/2402.02377/) (2024)
- [SCENIR: Visual Semantic Clarity through Unsupervised Scene Graph Retrieval](https://mlsanity.com/paper/2505.15867/) (2025)
- [Thermal Image Super-Resolution Using Second-Order Channel Attention with Varying Receptive Fields](https://mlsanity.com/paper/2108.00094/) (2021)
- [Learning Knowledge Representation with Meta Knowledge Distillation for Single Image Super-Resolution](https://mlsanity.com/paper/2207.08356/) (2022)
- [Toward Improving Synthetic Audio Spoofing Detection Robustness via Meta-Learning and Disentangled Training With Adversarial Examples](https://mlsanity.com/paper/2408.13341/) (2024)
- [Contrastive Graph Modeling for Cross-Domain Few-Shot Medical Image Segmentation](https://mlsanity.com/paper/2512.21683/) (2025)
- [Towards Generalization on Real Domain for Single Image Dehazing via Meta-Learning](https://mlsanity.com/paper/2211.07147/) (2022)
- [KernelDNA: Dynamic Kernel Sharing via Decoupled Naive Adapters](https://mlsanity.com/paper/2503.23379/) (2025)
- [MCL: Meta Convolution Layer](https://mlsanity.com/paper/2610.11117/) (2026)

## Abstract (arXiv)

As the basic building block of Convolutional Neural Networks (CNNs), the convolutional layer is designed to extract local patterns and lacks the ability to model global context in its nature. Many efforts have been recently devoted to complementing CNNs with the global modeling ability, especially by a family of works on global feature interaction. In these works, the global context information is incorporated into local features before they are fed into convolutional layers. However, research on neuroscience reveals that the neurons' ability of modifying their functions dynamically according to context is essential for the perceptual tasks, which has been overlooked in most of CNNs. Motivated by this, we propose one novel Context-Gated Convolution (CGC) to explicitly modify the weights of convolutional layers adaptively under the guidance of global context. As such, being aware of the global context, the modulated convolution kernel of our proposed CGC can better extract representative local patterns and compose discriminative features. Moreover, our proposed CGC is lightweight and applicable with modern CNN architectures, and consistently improves the performance of CNNs according to extensive experiments on image classification, action recognition, and machine translation. Our code of this paper is available at https://github.com/XudongLinthu/context-gated-convolution.