# Image Classification using Graph Neural Network and Multiscale Wavelet Superpixels

arXiv: https://arxiv.org/abs/2201.12633 · HTML: https://mlsanity.com/paper/2201.12633/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 37 references that are in the map.
- First posted on arXiv 29 Jan 2022.

## Builds on (most cited first, 13 of 13)

- [Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms](https://mlsanity.com/paper/1708.07747/) (2017)
- [Fast Graph Representation Learning with PyTorch Geometric](https://mlsanity.com/paper/1903.02428/) (2019)
- [Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering](https://mlsanity.com/paper/1606.09375/) (2016)
- [Benchmarking Graph Neural Networks](https://mlsanity.com/paper/2003.00982/) (2020)
- [Geometric deep learning on graphs and manifolds using mixture model CNNs](https://mlsanity.com/paper/1611.08402/) (2016)
- [Understanding Attention and Generalization in Graph Neural Networks](https://mlsanity.com/paper/1905.02850/) (2019)
- [SplineCNN: Fast Geometric Deep Learning with Continuous B-Spline Kernels](https://mlsanity.com/paper/1711.08920/) (2017)
- [Rethinking pooling in graph neural networks](https://mlsanity.com/paper/2010.11418/) (2020)
- [Superpixels: An Evaluation of the State-of-the-Art](https://mlsanity.com/paper/1612.01601/) (2016)
- [Superpixel Image Classification with Graph Attention Networks](https://mlsanity.com/paper/2002.05544/) (2020)
- [Image Classification with Hierarchical Multigraph Networks](https://mlsanity.com/paper/1907.09000/) (2019)
- [Evaluation Framework of Superpixel Methods with a Global Regularity Measure](https://mlsanity.com/paper/1903.07162/) (2019)
- [Image Segmentation Based on Multiscale Fast Spectral Clustering](https://mlsanity.com/paper/1812.04816/) (2018)

## Built on by (most cited first, 10 of 10)

- [SPA: A Graph Spectral Alignment Perspective for Domain Adaptation](https://mlsanity.com/paper/2310.17594/) (2023)
- [Learning to Parallelize with OpenMP by Augmented Heterogeneous AST Representation](https://mlsanity.com/paper/2305.05779/) (2023)
- [Ultra-Range Gesture Recognition using a Web-Camera in Human-Robot Interaction](https://mlsanity.com/paper/2311.15361/) (2023)
- [SPA++: Generalized Graph Spectral Alignment for Versatile Domain Adaptation](https://mlsanity.com/paper/2508.05182/) (2025)
- [Leveraging Spatial and Semantic Feature Extraction for Skin Cancer Diagnosis with Capsule Networks and Graph Neural Networks](https://mlsanity.com/paper/2403.12009/) (2024)
- [HC-GAE: The Hierarchical Cluster-based Graph Auto-Encoder for Graph Representation Learning](https://mlsanity.com/paper/2405.14742/) (2024)
- [Discovering distinctive elements of biomedical datasets for high-performance exploration](https://mlsanity.com/paper/2410.05436/) (2024)
- [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)
- [BadImplant: Injection-based Multi-Targeted Graph Backdoor Attack](https://mlsanity.com/paper/2601.15474/) (2026)

## Abstract (arXiv)

Prior studies using graph neural networks (GNNs) for image classification have focused on graphs generated from a regular grid of pixels or similar-sized superpixels. In the latter, a single target number of superpixels is defined for an entire dataset irrespective of differences across images and their intrinsic multiscale structure. On the contrary, this study investigates image classification using graphs generated from an image-specific number of multiscale superpixels. We propose WaveMesh, a new wavelet-based superpixeling algorithm, where the number and sizes of superpixels in an image are systematically computed based on its content. WaveMesh superpixel graphs are structurally different from similar-sized superpixel graphs. We use SplineCNN, a state-of-the-art network for image graph classification, to compare WaveMesh and similar-sized superpixels. Using SplineCNN, we perform extensive experiments on three benchmark datasets under three local-pooling settings: 1) no pooling, 2) GraclusPool, and 3) WavePool, a novel spatially heterogeneous pooling scheme tailored to WaveMesh superpixels. Our experiments demonstrate that SplineCNN learns from multiscale WaveMesh superpixels on-par with similar-sized superpixels. In all WaveMesh experiments, GraclusPool performs poorer than no pooling / WavePool, indicating that poor choice of pooling can result in inferior performance while learning from multiscale superpixels.