Triplet Synthesis For Enhancing Composed Image Retrieval via Counterfactual Image Generation

TL;DR

This paper introduces a novel triplet synthesis method using counterfactual image generation to automatically create diverse training data for composed image retrieval, reducing manual effort and improving model performance.

Contribution

It proposes a new automatic triplet synthesis approach leveraging counterfactual images, enhancing dataset diversity and model training efficiency for CIR.

Findings

Generated diverse triplets improve CIR accuracy.

Automatic synthesis reduces manual annotation effort.

Enhanced datasets lead to better retrieval performance.

Abstract

Composed Image Retrieval (CIR) provides an effective way to manage and access large-scale visual data. Construction of the CIR model utilizes triplets that consist of a reference image, modification text describing desired changes, and a target image that reflects these changes. For effectively training CIR models, extensive manual annotation to construct high-quality training datasets, which can be time-consuming and labor-intensive, is required. To deal with this problem, this paper proposes a novel triplet synthesis method by leveraging counterfactual image generation. By controlling visual feature modifications via counterfactual image generation, our approach automatically generates diverse training triplets without any manual intervention. This approach facilitates the creation of larger and more expressive datasets, leading to the improvement of CIR model's performance.