Fine-Grained Cat Breed Recognition with Global Context Vision Transformer

2026-02-07

AI Summary

This study addresses the challenge of fine-grained image recognition in cat breed classification, where subtle variations in fur color and facial structure often hinder accurate discrimination. To tackle this issue, the work proposes the first application of the Global Context Vision Transformer (GCViT-Tiny) to this domain. Leveraging a subset of the Oxford-IIIT Pet dataset, the approach incorporates data augmentation techniques—including rotation, horizontal flipping, and brightness adjustment—to effectively model global contextual information and enhance discriminative capacity. The proposed model achieves classification accuracies of 94.54% on the validation set and 92.00% on the test set, demonstrating the effectiveness and superiority of GCViT for fine-grained visual categorization tasks.

Technology Category

• Computer Vision: Object Detection & Categorization
• Machine Learning: Multi-class/Multi-label Learning & Extreme Classification
• Constraint Satisfaction and Optimization: Distributed CSP/Optimization

Application Category

• Web Mining and Content Analysis: Large pretrained models with web data
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs

Abstract

Accurate identification of cat breeds from images is a challenging task due to subtle differences in fur patterns, facial structure, and color. In this paper, we present a deep learning-based approach for classifying cat breeds using a subset of the Oxford-IIIT Pet Dataset, which contains high-resolution images of various domestic breeds. We employed the Global Context Vision Transformer (GCViT) architecture-tiny for cat breed recognition. To improve model generalization, we used extensive data augmentation, including rotation, horizontal flipping, and brightness adjustment. Experimental results show that the GCViT-Tiny model achieved a test accuracy of 92.00% and validation accuracy of 94.54%. These findings highlight the effectiveness of transformer-based architectures for fine-grained image classification tasks. Potential applications include veterinary diagnostics, animal shelter management, and mobile-based breed recognition systems. We also provide a hugging face demo at https://huggingface.co/spaces/bfarhad/cat-breed-classifier.

Problem

• fine-grained classification
• cat breed recognition
• image classification
• visual recognition

Innovation

• Global Context Vision Transformer
• fine-grained classification
• cat breed recognition
• data augmentation
• Vision Transformer