# Spatial Pyramid Based Graph Reasoning for Semantic Segmentation

arXiv: https://arxiv.org/abs/2003.10211 · HTML: https://mlsanity.com/paper/2003.10211/

## Key facts

- Cited by 47 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Mar 2020.

## Built on by (most cited first, 30 of 47)

- [Exploring Cross-Image Pixel Contrast for Semantic Segmentation](https://mlsanity.com/paper/2101.11939/) (2021)
- [Attention Mechanisms in Computer Vision: A Survey](https://mlsanity.com/paper/2111.07624/) (2021)
- [Rethinking Semantic Segmentation: A Prototype View](https://mlsanity.com/paper/2203.15102/) (2022)
- [Beyond Self-attention: External Attention using Two Linear Layers for Visual Tasks](https://mlsanity.com/paper/2105.02358/) (2021)
- [SegViT: Semantic Segmentation with Plain Vision Transformers](https://mlsanity.com/paper/2210.05844/) (2022)
- [Mutual Graph Learning for Camouflaged Object Detection](https://mlsanity.com/paper/2104.02613/) (2021)
- [Large-scale Unsupervised Semantic Segmentation](https://mlsanity.com/paper/2106.03149/) (2021)
- [Is Attention Better Than Matrix Decomposition?](https://mlsanity.com/paper/2109.04553/) (2021)
- [A Survey on Graph Neural Networks and Graph Transformers in Computer Vision: A Task-Oriented Perspective](https://mlsanity.com/paper/2209.13232/) (2022)
- [Learning Statistical Texture for Semantic Segmentation](https://mlsanity.com/paper/2103.04133/) (2021)
- [Multi-Source Domain Adaptation with Collaborative Learning for Semantic Segmentation](https://mlsanity.com/paper/2103.04717/) (2021)
- [ISNet: Integrate Image-Level and Semantic-Level Context for Semantic Segmentation](https://mlsanity.com/paper/2108.12382/) (2021)
- [PolyphonicFormer: Unified Query Learning for Depth-aware Video Panoptic Segmentation](https://mlsanity.com/paper/2112.02582/) (2021)
- [High Quality Segmentation for Ultra High-resolution Images](https://mlsanity.com/paper/2111.14482/) (2021)
- [StructToken : Rethinking Semantic Segmentation with Structural Prior](https://mlsanity.com/paper/2203.12612/) (2022)
- [PointFlow: Flowing Semantics Through Points for Aerial Image Segmentation](https://mlsanity.com/paper/2103.06564/) (2021)
- [Mining Relations among Cross-Frame Affinities for Video Semantic Segmentation](https://mlsanity.com/paper/2207.10436/) (2022)
- [SegViTv2: Exploring Efficient and Continual Semantic Segmentation with Plain Vision Transformers](https://mlsanity.com/paper/2306.06289/) (2023)
- [Learning Local and Global Temporal Contexts for Video Semantic Segmentation](https://mlsanity.com/paper/2204.03330/) (2022)
- [SPIN Road Mapper: Extracting Roads from Aerial Images via Spatial and Interaction Space Graph Reasoning for Autonomous Driving](https://mlsanity.com/paper/2109.07701/) (2021)
- [AGRNet: Adaptive Graph Representation Learning and Reasoning for Face Parsing](https://mlsanity.com/paper/2101.07034/) (2021)
- [Channelized Axial Attention for Semantic Segmentation -- Considering Channel Relation within Spatial Attention for Semantic Segmentation](https://mlsanity.com/paper/2101.07434/) (2021)
- [Vanishing-Point-Guided Video Semantic Segmentation of Driving Scenes](https://mlsanity.com/paper/2401.15261/) (2024)
- [ARM3D: Attention-based relation module for indoor 3D object detection](https://mlsanity.com/paper/2202.09715/) (2022)
- [Semi-Supervised Semantic Segmentation with Cross Teacher Training](https://mlsanity.com/paper/2209.01327/) (2022)
- [BI-GCN: Boundary-Aware Input-Dependent Graph Convolution Network for Biomedical Image Segmentation](https://mlsanity.com/paper/2110.14775/) (2021)
- [Global Aggregation then Local Distribution for Scene Parsing](https://mlsanity.com/paper/2107.13154/) (2021)
- [Cross-attention Spatio-temporal Context Transformer for Semantic Segmentation of Historical Maps](https://mlsanity.com/paper/2310.12616/) (2023)
- [Tracing Hyperparameter Dependencies for Model Parsing via Learnable Graph Pooling Network](https://mlsanity.com/paper/2312.02224/) (2023)
- [E-CRF: Embedded Conditional Random Field for Boundary-caused Class Weights Confusion in Semantic Segmentation](https://mlsanity.com/paper/2112.07106/) (2021)

## Abstract (arXiv)

The convolution operation suffers from a limited receptive filed, while global modeling is fundamental to dense prediction tasks, such as semantic segmentation. In this paper, we apply graph convolution into the semantic segmentation task and propose an improved Laplacian. The graph reasoning is directly performed in the original feature space organized as a spatial pyramid. Different from existing methods, our Laplacian is data-dependent and we introduce an attention diagonal matrix to learn a better distance metric. It gets rid of projecting and re-projecting processes, which makes our proposed method a light-weight module that can be easily plugged into current computer vision architectures. More importantly, performing graph reasoning directly in the feature space retains spatial relationships and makes spatial pyramid possible to explore multiple long-range contextual patterns from different scales. Experiments on Cityscapes, COCO Stuff, PASCAL Context and PASCAL VOC demonstrate the effectiveness of our proposed methods on semantic segmentation. We achieve comparable performance with advantages in computational and memory overhead.