OpenFashionCLIP: Vision-and-Language Contrastive Learning with Open-Source Fashion Data

TL;DR

OpenFashionCLIP introduces a vision-and-language contrastive learning framework trained solely on open-source fashion data, demonstrating strong out-of-domain generalization and outperforming existing methods in accuracy and recall across multiple benchmarks.

Contribution

It presents a novel contrastive learning approach using open-source, diverse fashion data, enhancing generalization and performance in fashion-related multimodal tasks.

Findings

Significant out-of-domain generalization capability.

Consistent improvements over state-of-the-art in accuracy.

Enhanced recall in multimodal retrieval tasks.

Abstract

The inexorable growth of online shopping and e-commerce demands scalable and robust machine learning-based solutions to accommodate customer requirements. In the context of automatic tagging classification and multimodal retrieval, prior works either defined a low generalizable supervised learning approach or more reusable CLIP-based techniques while, however, training on closed source data. In this work, we propose OpenFashionCLIP, a vision-and-language contrastive learning method that only adopts open-source fashion data stemming from diverse domains, and characterized by varying degrees of specificity. Our approach is extensively validated across several tasks and benchmarks, and experimental results highlight a significant out-of-domain generalization capability and consistent improvements over state-of-the-art methods both in terms of accuracy and recall. Source code and trained models are publicly available at: https://github.com/aimagelab/open-fashion-clip.