FashionFAE: Fine-grained Attributes Enhanced Fashion Vision-Language Pre-training

TL;DR

FashionFAE introduces a novel vision-language pre-training approach emphasizing fine-grained attributes like texture and material, significantly improving fashion item retrieval and recognition tasks.

Contribution

It proposes attribute-focused text prediction and image reconstruction tasks to enhance fine-grained understanding in fashion vision-language models.

Findings

Achieves 2.9% and 5.2% improvements in retrieval accuracy.

Attains 1.6% average improvement in recognition tasks.

Outperforms state-of-the-art methods on fashion datasets.

Abstract

Large-scale Vision-Language Pre-training (VLP) has demonstrated remarkable success in the general domain. However, in the fashion domain, items are distinguished by fine-grained attributes like texture and material, which are crucial for tasks such as retrieval. Existing models often fail to leverage these fine-grained attributes from both text and image modalities. To address the above issues, we propose a novel approach for the fashion domain, Fine-grained Attributes Enhanced VLP (FashionFAE), which focuses on the detailed characteristics of fashion data. An attribute-emphasized text prediction task is proposed to predict fine-grained attributes of the items. This forces the model to focus on the salient attributes from the text modality. Additionally, a novel attribute-promoted image reconstruction task is proposed, which further enhances the fine-grained ability of the model by leveraging the representative attributes from the image modality. Extensive experiments show that FashionFAE significantly outperforms State-Of-The-Art (SOTA) methods, achieving 2.9% and 5.2% improvements in retrieval on sub-test and full test sets, respectively, and a 1.6% average improvement in recognition tasks.