Triplet Synthesis For Enhancing Composed Image Retrieval via Counterfactual Image Generation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Uesugi, Kenta, Saito, Naoki, Maeda, Keisuke, Ogawa, Takahiro, Haseyama, Miki
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909465108807680
author Uesugi, Kenta
Saito, Naoki
Maeda, Keisuke
Ogawa, Takahiro
Haseyama, Miki
author_facet Uesugi, Kenta
Saito, Naoki
Maeda, Keisuke
Ogawa, Takahiro
Haseyama, Miki
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2501_13968
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Triplet Synthesis For Enhancing Composed Image Retrieval via Counterfactual Image Generation
Uesugi, Kenta
Saito, Naoki
Maeda, Keisuke
Ogawa, Takahiro
Haseyama, Miki
Computer Vision and Pattern Recognition
Machine Learning
Image and Video Processing
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.
title Triplet Synthesis For Enhancing Composed Image Retrieval via Counterfactual Image Generation
topic Computer Vision and Pattern Recognition
Machine Learning
Image and Video Processing
url https://arxiv.org/abs/2501.13968