# Superpixel Image Classification with Graph Attention Networks

arXiv: https://arxiv.org/abs/2002.05544 · HTML: https://mlsanity.com/paper/2002.05544/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Feb 2020.

## Built on by (most cited first, 20 of 20)

- [Multimodal learning with graphs](https://mlsanity.com/paper/2209.03299/) (2022)
- [A Hard Label Black-box Adversarial Attack Against Graph Neural Networks](https://mlsanity.com/paper/2108.09513/) (2021)
- [Image Classification using Graph Neural Network and Multiscale Wavelet Superpixels](https://mlsanity.com/paper/2201.12633/) (2022)
- [PolyNet: Polynomial Neural Network for 3D Shape Recognition with PolyShape Representation](https://mlsanity.com/paper/2110.07882/) (2021)
- [Differentiable Sensor Layouts for End-to-End Learning of Task-Specific Camera Parameters](https://mlsanity.com/paper/2304.14736/) (2023)
- [Graph Representation Learning for Spatial Image Steganalysis](https://mlsanity.com/paper/2110.00957/) (2021)
- [GraphVid: It Only Takes a Few Nodes to Understand a Video](https://mlsanity.com/paper/2207.01375/) (2022)
- [Explaining Vision GNNs: A Semantic and Visual Analysis of Graph-based Image Classification](https://mlsanity.com/paper/2504.19682/) (2025)
- [JPEG Steganalysis Based on Steganographic Feature Enhancement and Graph Attention Learning](https://mlsanity.com/paper/2302.02276/) (2023)
- [GeNet: A Graph Neural Network-based Anti-noise Task-Oriented Semantic Communication Paradigm](https://mlsanity.com/paper/2403.18296/) (2024)
- [Superpixel-based Knowledge Infusion in Deep Neural Networks for Image Classification](https://mlsanity.com/paper/2105.09448/) (2021)
- [Exploring Explainability Methods for Graph Neural Networks](https://mlsanity.com/paper/2211.01770/) (2022)
- [Geometric Deep Learning: a Temperature Based Analysis of Graph Neural Networks](https://mlsanity.com/paper/2309.00699/) (2023)
- [Domain-Adversarial Anatomical Graph Networks for Cross-User Human Activity Recognition](https://mlsanity.com/paper/2505.06301/) (2025)
- [Accelerating Image Classification with Graph Convolutional Neural Networks using Voronoi Diagrams](https://mlsanity.com/paper/2508.14218/) (2025)
- [Fast Graph Neural Network for Image Classification](https://mlsanity.com/paper/2508.14958/) (2025)
- [Superpixel Integrated Grids for Fast Image Segmentation](https://mlsanity.com/paper/2510.06487/) (2025)
- [iPac: Incorporating Intra-image Patch Context into Graph Neural Networks for Medical Image Classification](https://mlsanity.com/paper/2510.23504/) (2025)
- [Is an Image Also Worth 16x16=256 Superpixels? A Framework for Attentional Image Classification](https://mlsanity.com/paper/2605.27144/) (2026)
- [On Preserving Geometrical Invariance for Superpixel Image Classification using Graph Transformer](https://mlsanity.com/paper/2607.04262/) (2026)

## Abstract (arXiv)

This paper presents a methodology for image classification using Graph Neural Network (GNN) models. We transform the input images into region adjacency graphs (RAGs), in which regions are superpixels and edges connect neighboring superpixels. Our experiments suggest that Graph Attention Networks (GATs), which combine graph convolutions with self-attention mechanisms, outperforms other GNN models. Although raw image classifiers perform better than GATs due to information loss during the RAG generation, our methodology opens an interesting avenue of research on deep learning beyond rectangular-gridded images, such as 360-degree field of view panoramas. Traditional convolutional kernels of current state-of-the-art methods cannot handle panoramas, whereas the adapted superpixel algorithms and the resulting region adjacency graphs can naturally feed a GNN, without topology issues.