Hierarchical Similarity Learning for Language-based Product Image Retrieval

TL;DR

This paper introduces a Hierarchical Similarity Learning network that captures multi-level representations for more accurate language-based product image retrieval, outperforming previous methods by considering multiple granularities.

Contribution

The paper proposes a novel HSL network that models multi-granularity similarities at different levels, enhancing cross-modal retrieval performance.

Findings

Effective on large-scale product dataset

Improves matching accuracy by considering multiple granularities

Code and data are publicly available

Abstract

This paper aims for the language-based product image retrieval task. The majority of previous works have made significant progress by designing network structure, similarity measurement, and loss function. However, they typically perform vision-text matching at certain granularity regardless of the intrinsic multiple granularities of images. In this paper, we focus on the cross-modal similarity measurement, and propose a novel Hierarchical Similarity Learning (HSL) network. HSL first learns multi-level representations of input data by stacked encoders, and object-granularity similarity and image-granularity similarity are computed at each level. All the similarities are combined as the final hierarchical cross-modal similarity. Experiments on a large-scale product retrieval dataset demonstrate the effectiveness of our proposed method. Code and data are available at https://github.com/liufh1/hsl.