IndoFashion : Apparel Classification for Indian Ethnic Clothes

TL;DR

This paper introduces a large-scale dataset of over 106,000 images for fine-grained classification of Indian ethnic clothes, addressing the limitations of models trained on western clothing datasets.

Contribution

The creation of the first extensive ethnic clothing dataset with 15 categories, enabling improved classification and fostering further research in ethnic apparel recognition.

Findings

Achieved 88.43% classification accuracy on the dataset.

Evaluated multiple baseline models for ethnic clothing classification.

Dataset sourced from diverse Indian e-commerce websites.

Abstract

Cloth categorization is an important research problem that is used by e-commerce websites for displaying correct products to the end-users. Indian clothes have a large number of clothing categories both for men and women. The traditional Indian clothes like "Saree" and "Dhoti" are worn very differently from western clothes like t-shirts and jeans. Moreover, the style and patterns of ethnic clothes have a very different distribution from western outfits. Thus the models trained on standard cloth datasets fail miserably on ethnic outfits. To address these challenges, we introduce the first large-scale ethnic dataset of over 106k images with 15 different categories for fine-grained classification of Indian ethnic clothes. We gathered a diverse dataset from a large number of Indian e-commerce websites. We then evaluate several baselines for the cloth classification task on our dataset. In the end, we obtain 88.43% classification accuracy. We hope that our dataset would foster research in the development of several algorithms such as cloth classification, landmark detection, especially for ethnic clothes.