# On Preserving Geometrical Invariance for Superpixel Image Classification using Graph Transformer

Source: [On Preserving Geometrical Invariance for Superpixel Image Classification using Graph Transformer](<https://www.sota2.com/research/paper/6a4c882d85dba69fef8b2b1b>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-07-08T05:00:20.838Z

Authors: Sarabeshwar Balaji, Shubham Mohanty, Akash Anil

Published: 2026-07-05T12:16:23.000Z

## Abstract

Convolutional Neural Network (CNN) and Vision Transformer (ViT) for image classification exploit a dense grid of pixels containing redundant information. Consequently, for a larger image dataset, CNNs and ViTs face deployability challenges due to high computational complexity. Representing images as graphs of superpixels offers an efficient alternative that preserves key information while eliminating pixel-level redundancy. Graph Neural Networks (GNNs) have been utilized on such graphs to perform image classification. However, GNNs are known to struggle with capturing long-range dependencies which is important in the domain of image classification. Furthermore, a majority of these superpixel-based image classification approaches do not explicitly preserve translation/rotation invariance. Nevertheless, preserving translation/rotation invariance is important for robust image classification. Thus, this paper proposes SuperGT, a Graph Transformer-based framework for image classification, which captures the long range dependencies, along with a pre-processing scheme that preserves translation/rotation invariance. We evaluate SuperGT on CIFAR-10 dataset and observe that it performs significantly better than many baselines. Furthermore, we note that the overall performance of SuperGT is comparable to the previous state-of-the-art model, namely, ShapeGNN, without relying on coordinates of the boundary points of each superpixel required by ShapeGNN.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Image Classification on CIFAR-10 Superpixels](<https://www.sota2.com/research/sota/image-classification-on-cifar-10-superpixels.md>): Image Classification; CIFAR-10 Superpixels; Accuracy: 80.19.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2607.04262>)

[PDF](<https://arxiv.org/pdf/2607.04262.pdf>)