On Preserving Geometrical Invariance for Superpixel Image Classification using Graph Transformer

• URL: http://arxiv.org/abs/2607.04262v1
• Date: Sun, 05 Jul 2026 12:16:23 GMT
• Title: On Preserving Geometrical Invariance for Superpixel Image Classification using Graph Transformer
• Abstract summary: Convolutional Neural Network (CNN) and Vision Transformer (ViT) for image classification exploit a dense grid of pixels containing redundant information.<n>For a larger image dataset, CNNs and ViTs face deployability challenges due to high computational complexity.<n>This paper proposes SuperGT, a Graph Transformer-based framework for image classification, which captures the long range dependencies.
• Score: 0.19116784879310025
• License: http://creativecommons.org/licenses/by/4.0/
• 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.

Related papers

• Is an Image Also Worth 16x16=256 Superpixels? A Framework for Attentional Image Classification [0.11470070927586014]
  We propose Superpixel Transformers (SPT), a novel framework that unifies superpixel-based image classification and Vision Transformers (ViTs)<n>SPT generalizes the Superpixel Image Classification with Graph Attention Networks (SICGAT) model and ViT to support arbitrary superpixel-based chunking strategies, connectivity graphs, and positional encodings.<n>We show that SPT achieves superior performance compared to previous superpixel-based GNN methods and remains competitive with ViTs.
  arXiv  Detail & Related papers  (2026-05-26T15:09:46Z)
• Square Superpixel Generation and Representation Learning via Granular Ball Computing [97.99956628286243]
  Superpixels provide a compact region-based representation that preserves object boundaries and local structures.<n>Most existing superpixel algorithms produce irregularly shaped regions, which are not well aligned with regular operators such as convolutions.<n>Motivated by the adaptive representation and coverage property of granular-ball computing, we develop a square superpixel generation approach.
  arXiv  Detail & Related papers  (2026-03-31T09:06:58Z)
• Superpixel Integrated Grids for Fast Image Segmentation [0.07639235704257864]
  We introduce a new superpixel-based data structure, SIGRID, as an alternative to full-resolution images in segmentation tasks.<n>By leveraging classical shape descriptors, SIGRID encodes both color and shape information of superpixels while substantially reducing input dimensionality.
  arXiv  Detail & Related papers  (2025-10-07T22:02:48Z)
• Structural-Spectral Graph Convolution with Evidential Edge Learning for Hyperspectral Image Clustering [73.01141916544103]
  Hyperspectral image (HSI) clustering groups pixels into clusters without labeled data.<n>Most methods rely on superpixel segmentation and perform superpixel-level clustering based on graph neural networks (GNNs)<n>We propose a structural-spectral graph convolutional operator (SSGCO) tailored for graph-structured HSI superpixels to improve representation quality.
  arXiv  Detail & Related papers  (2025-06-11T16:41:34Z)
• Graph-Weighted Contrastive Learning for Semi-Supervised Hyperspectral Image Classification [9.640130509216629]
  We propose a graph-weighted contrastive learning approach that avoids the use of superpixel partitioning and directly employs neural networks to learn hyperspectral image representation.<n>Our approach supports mini-batch training by processing only a subset of nodes at a time, reducing computational complexity and improving generalization to unseen nodes.
  arXiv  Detail & Related papers  (2025-03-19T22:55:52Z)
• SAG-ViT: A Scale-Aware, High-Fidelity Patching Approach with Graph Attention for Vision Transformers [0.0]
  Vision Transformers (ViTs) have redefined image classification by leveraging self-attention to capture complex patterns and long-range dependencies between image patches.<n>A key challenge for ViTs is efficiently incorporating multi-scale feature representations, which is inherent in convolutional neural networks (CNNs) through their hierarchical structure.<n>We propose SAG-ViT, a Scale-Aware Graph Attention ViT that integrates multi-scale feature capabilities of CNNs, representational power of ViTs, graph-attended patching to enable richer contextual representation.
  arXiv  Detail & Related papers  (2024-11-14T13:15:27Z)
• Fine-grained Recognition with Learnable Semantic Data Augmentation [68.48892326854494]
  Fine-grained image recognition is a longstanding computer vision challenge. We propose diversifying the training data at the feature-level to alleviate the discriminative region loss problem. Our method significantly improves the generalization performance on several popular classification networks.
  arXiv  Detail & Related papers  (2023-09-01T11:15:50Z)
• T-former: An Efficient Transformer for Image Inpainting [50.43302925662507]
  A class of attention-based network architectures, called transformer, has shown significant performance on natural language processing fields. In this paper, we design a novel attention linearly related to the resolution according to Taylor expansion, and based on this attention, a network called $T$-former is designed for image inpainting. Experiments on several benchmark datasets demonstrate that our proposed method achieves state-of-the-art accuracy while maintaining a relatively low number of parameters and computational complexity.
  arXiv  Detail & Related papers  (2023-05-12T04:10:42Z)
• Scalable Visual Transformers with Hierarchical Pooling [61.05787583247392]
  We propose a Hierarchical Visual Transformer (HVT) which progressively pools visual tokens to shrink the sequence length. It brings a great benefit by scaling dimensions of depth/width/resolution/patch size without introducing extra computational complexity. Our HVT outperforms the competitive baselines on ImageNet and CIFAR-100 datasets.
  arXiv  Detail & Related papers  (2021-03-19T03:55:58Z)
• Group-Wise Semantic Mining for Weakly Supervised Semantic Segmentation [49.90178055521207]
  This work addresses weakly supervised semantic segmentation (WSSS), with the goal of bridging the gap between image-level annotations and pixel-level segmentation. We formulate WSSS as a novel group-wise learning task that explicitly models semantic dependencies in a group of images to estimate more reliable pseudo ground-truths. In particular, we devise a graph neural network (GNN) for group-wise semantic mining, wherein input images are represented as graph nodes.
  arXiv  Detail & Related papers  (2020-12-09T12:40:13Z)
• Superpixel Image Classification with Graph Attention Networks [4.714325419968082]
  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. Experiments suggest that Graph Attention Networks (GATs), which combine graph convolutions with self-attention mechanisms, outperforms other GNN models.
  arXiv  Detail & Related papers  (2020-02-13T14:52:32Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.