Clothing Classification using Vision Transformer, Efficient-NET and CNN
DOI:
https://doi.org/10.63503/acset.132Keywords:
Clothing classification, deep learning, Efficient-Net, CNN, Kaggle dataset, Vision Transformer, fashion recommendation, image classificationAbstract
Clothing classification is an important task in computer vision. It has key uses in fashion retail, inventory management, and recommendation systems. This paper presents a deep learning framework for clothing classification. It compares Vision Transformer (ViT), EfficientNet, and Convolutional Neural Networks (CNN). The Vision Transformer captures global relationships across image patches. EfficientNet offers a good balance between model accuracy and computational efficiency through compound scaling. CNN models extract local features, such as textures and patterns, that help distinguish visually similar clothing categories. Research was conducted to evaluate the proposed approach on a large labelled clothing dataset. This dataset includes various lighting conditions, backgrounds, and poses. The experimental results show that EfficientNet achieves the highest classification accuracy of 94.09%. It outperforms both the CNN and ViT models in accuracy and efficiency. These findings underscore the effectiveness of modern deep learning models for reliable and scalable clothing classification in real-world situations.
References
[1] S.Bouzidi, G. Hcini, I. Jdey, and F. Drira, “Synergizing cnns and vits: A survey on hybrid models for fashion image classification,” Revista de Informatica´ Teorica´ e Aplicada, vol. 33, no. 1, pp. 11–27, 2026.
[2] X. Nie and L. Zhao, “Intelligent clothing design system based on aigc and virtual simulation technology,” International Journal of Computer Information Systems and Industrial Management Applications, vol. 18, pp. 18–18, 2026.
[3] S. Wang, M. Song, J. Shi, S. Shi, F. Yang, and L. Yang, “Clothing semantic-driven progressive guidance learning for clothing-change person re-identification,” Engineering Applications of Artificial Intelligence, vol. 164, p. 113290, 2026.
[4] C. K. Basak, G. Sarkar, and P. K. Kundu, “Deep transfer learning framework for thermal tomographic image classification: a comparative study,” Multiscale and Multidisciplinary Modeling, Experiments and Design, vol. 9, no. 1, p. 77, 2026.
[5] A. Kumar, B. Paul, R. Chaudhary, and K. Kumar, “From text to recommendations: Classifying e-commerce clothing reviews using deep neural networks,” in 2025 International Conference on Artificial Intelligence and Machine Vision (AIMV). IEEE, 2025, pp. 1 – 6.
[6] E. Cetin, M. B. Ozbek,¨ S. Biner, C. Ulus, and M. F. Akay, “Development of a system for creating and recommending combination collections in the e-commerce clothing industry,” Computing and Artificial Intelligence, pp. 1987–1987, 2025.
[7] Z. Sun, B. Song, S. Gao, S. Zhao, L. Yang, and Y. Zhai, “Dynamic detection models for clothing insulation and metabolic rate based on computer vision,” Building and Environment, vol. 283, p. 113372, 2025
[8] A. Demelash and E. Derb, “Habesha cultural cloth classification using deep learning,” Scientific Reports, vol. 15, no. 1, p. 14000, 2025.
[9] S. V. Kumar, P. Kumar, and S. Saravanan, “Enhancing e-commerce using fashion recommendation system,” in 2025 International Conference on Visual Analytics and Data Visualization (ICVADV). IEEE, 2025, pp. 864–868.
[10] A. B. Pitta, N. R. Pingala, N. V. M. C. Jaladhi, S. Bogolu, and B. Suvarna, “Footwear classification using pretrained cnn models with deep neural network,” in 2025 International Conference on Multi-Agent Systems for Collaborative Intelligence (ICMSCI). IEEE, 2025, pp. 1729–1736.
[11] C. Rajani, S. Moturi, M. K. Rao, P. Saiganesh, S. K. Moula, and P. K. Khan, “Enhancing fashion product recommendations through cnn-based ensemble learning,” in Congress on Control, Robotics, and Mechatronics. Springer, 2025, pp. 193–207.
[12] Z. Wang, A. Aris, and P. Zhang, “Mobile-driven deep learning algorithm for personalized clothing design using multi-feature attributes.” International Journal of Interactive Mobile Technologies, vol. 19, no. 18, 2025.
[13] Y. Hassan, S. Abdelhamid, A. Fathi, P. Edward, and O. G. Elkhouly, “Optimized neural networks for fashion-mnist: A high-accuracy approach using augmentation and tuning,” in 2025 International Mobile, Intelligent, and Ubiquitous Computing Conference (MIUCC). IEEE, 2025, pp. 21–27.
[14] S.-Y. Shin, G. Jo, and G. Wang, “A novel method for fashion clothing image classification based on deep learning,” Journal of Information and Communication Technology, vol. 22, no. 1, pp. 127–148, 2023.
[15] A. Medina, J. I. Mendez,´ P. Ponce, T. Peffer, A. Meier, and A. Molina, “Using deep learning in real-time for clothing classification with connected thermostats,” Energies, vol. 15, no. 5, p. 1811, 2022.
Downloads
Published
Conference Proceedings Volume
Section
License
Copyright (c) 2026 Adroid Conference Series: Engineering and Technology
This work is licensed under a Creative Commons Attribution 4.0 International License.
