Fine-Grained Cat Breed Recognition with Global Context Vision Transformer

Citation

Hera MP, Kallol MSM, Nirob SR, Bulbul MB, Ahmed J, Islam MZ, Ali H & Bulbul MF (2026) Fine-Grained Cat Breed Recognition with Global Context Vision Transformer. In: 2025 28th International Conference on Computer and Information Technology (ICCIT), Cox's Bazar, Bangladesh, 19.12.2025-21.12.2025. IEEE, pp. 2271-2275. https://doi.org/10.1109/iccit68739.2025.11490185

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 highresolution 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.

Keywords
Cat breed classification; Deep learning; OxfordIIIT Pet Dataset; Vision transformer; Fine-grained image classification

Journal
2025 28th International Conference on Computer and Information Technology (ICCIT)