Partial Visual-Semantic Embedding: Fashion Intelligence System with Sensitive Part-by-Part Learning

TL;DR

This paper introduces a partial visual-semantic embedding model for fashion that enables part-specific learning, improving image retrieval and reordering tasks involving individual fashion components.

Contribution

The paper presents a novel partial VSE model that supports part-by-part learning in fashion images, enhancing retrieval and reordering functionalities.

Findings

Partial VSE outperforms conventional models in accuracy.

Supports image retrieval with modifications to specific parts.

Maintains computational efficiency despite added functionality.

Abstract

In this study, we propose a technology called the Fashion Intelligence System based on the visual-semantic embedding (VSE) model to quantify abstract and complex expressions unique to fashion, such as ''casual,'' ''adult-casual,'' and ''office-casual,'' and to support users' understanding of fashion. However, the existing VSE model does not support the situations in which the image is composed of multiple parts such as hair, tops, pants, skirts, and shoes. We propose partial VSE, which enables sensitive learning for each part of the fashion coordinates. The proposed model partially learns embedded representations. This helps retain the various existing practical functionalities and enables image-retrieval tasks in which changes are made only to the specified parts and image reordering tasks that focus on the specified parts. This was not possible with conventional models. Based on both the qualitative and quantitative evaluation experiments, we show that the proposed model is superior to conventional models without increasing the computational complexity.