# Dynamic Graph Message Passing Networks

arXiv: https://arxiv.org/abs/1908.06955 · HTML: https://mlsanity.com/paper/1908.06955/

## Key facts

- Cited by 62 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Aug 2019.

## Built on by (most cited first, 30 of 62)

- [ViViT: A Video Vision Transformer](https://mlsanity.com/paper/2103.15691/) (2021)
- [SOFT: Softmax-free Transformer with Linear Complexity](https://mlsanity.com/paper/2110.11945/) (2021)
- [Graph-Guided Network for Irregularly Sampled Multivariate Time Series](https://mlsanity.com/paper/2110.05357/) (2021)
- [Involution: Inverting the Inherence of Convolution for Visual Recognition](https://mlsanity.com/paper/2103.06255/) (2021)
- [Depth-conditioned Dynamic Message Propagation for Monocular 3D Object Detection](https://mlsanity.com/paper/2103.16470/) (2021)
- [Self-supervised Video Transformer](https://mlsanity.com/paper/2112.01514/) (2021)
- [A Survey on Graph Neural Networks and Graph Transformers in Computer Vision: A Task-Oriented Perspective](https://mlsanity.com/paper/2209.13232/) (2022)
- [Long-Short Temporal Contrastive Learning of Video Transformers](https://mlsanity.com/paper/2106.09212/) (2021)
- [Spatio-Temporal Dynamic Inference Network for Group Activity Recognition](https://mlsanity.com/paper/2108.11743/) (2021)
- [Learning Dynamic Alignment via Meta-filter for Few-shot Learning](https://mlsanity.com/paper/2103.13582/) (2021)
- [A survey on efficient vision transformers: algorithms, techniques, and performance benchmarking](https://mlsanity.com/paper/2309.02031/) (2023)
- [Active Boundary Loss for Semantic Segmentation](https://mlsanity.com/paper/2102.02696/) (2021)
- [Unified Graph Structured Models for Video Understanding](https://mlsanity.com/paper/2103.15662/) (2021)
- [Learning Dynamics via Graph Neural Networks for Human Pose Estimation and Tracking](https://mlsanity.com/paper/2106.03772/) (2021)
- [Generative Semantic Segmentation](https://mlsanity.com/paper/2303.11316/) (2023)
- [PointFlow: Flowing Semantics Through Points for Aerial Image Segmentation](https://mlsanity.com/paper/2103.06564/) (2021)
- [Proposal-Free Temporal Action Detection via Global Segmentation Mask Learning](https://mlsanity.com/paper/2207.06580/) (2022)
- [Few-shot Action Recognition with Prototype-centered Attentive Learning](https://mlsanity.com/paper/2101.08085/) (2021)
- [DuAT: Dual-Aggregation Transformer Network for Medical Image Segmentation](https://mlsanity.com/paper/2212.11677/) (2022)
- [Instance and Panoptic Segmentation Using Conditional Convolutions](https://mlsanity.com/paper/2102.03026/) (2021)
- [SeaFormer++: Squeeze-enhanced Axial Transformer for Mobile Visual Recognition](https://mlsanity.com/paper/2301.13156/) (2023)
- [Hashing-Accelerated Graph Neural Networks for Link Prediction](https://mlsanity.com/paper/2105.14280/) (2021)
- [A Unified Efficient Pyramid Transformer for Semantic Segmentation](https://mlsanity.com/paper/2107.14209/) (2021)
- [Query-guided Prototype Evolution Network for Few-Shot Segmentation](https://mlsanity.com/paper/2403.06488/) (2024)
- [Cascade Image Matting with Deformable Graph Refinement](https://mlsanity.com/paper/2105.02646/) (2021)
- [PVG: Progressive Vision Graph for Vision Recognition](https://mlsanity.com/paper/2308.00574/) (2023)
- [Softmax-free Linear Transformers](https://mlsanity.com/paper/2207.03341/) (2022)
- [Global Aggregation then Local Distribution for Scene Parsing](https://mlsanity.com/paper/2107.13154/) (2021)
- [Aerial Images Meet Crowdsourced Trajectories: A New Approach to Robust Road Extraction](https://mlsanity.com/paper/2111.15119/) (2021)
- [Vision Transformers: From Semantic Segmentation to Dense Prediction](https://mlsanity.com/paper/2207.09339/) (2022)

## Abstract (arXiv)

Modelling long-range dependencies is critical for scene understanding tasks in computer vision. Although CNNs have excelled in many vision tasks, they are still limited in capturing long-range structured relationships as they typically consist of layers of local kernels. A fully-connected graph is beneficial for such modelling, however, its computational overhead is prohibitive. We propose a dynamic graph message passing network, that significantly reduces the computational complexity compared to related works modelling a fully-connected graph. This is achieved by adaptively sampling nodes in the graph, conditioned on the input, for message passing. Based on the sampled nodes, we dynamically predict node-dependent filter weights and the affinity matrix for propagating information between them. Using this model, we show significant improvements with respect to strong, state-of-the-art baselines on three different tasks and backbone architectures. Our approach also outperforms fully-connected graphs while using substantially fewer floating-point operations and parameters. The project website is http://www.robots.ox.ac.uk/~lz/dgmn/