Active Learning for Finely-Categorized Image-Text Retrieval by Selecting Hard Negative Unpaired Samples

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Jo, Dae Ung, Lee, Kyuewang, Chung, JaeHo, Choi, Jin Young
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914811741208576
author Jo, Dae Ung
Lee, Kyuewang
Chung, JaeHo
Choi, Jin Young
author_facet Jo, Dae Ung
Lee, Kyuewang
Chung, JaeHo
Choi, Jin Young
contents Securing a sufficient amount of paired data is important to train an image-text retrieval (ITR) model, but collecting paired data is very expensive. To address this issue, in this paper, we propose an active learning algorithm for ITR that can collect paired data cost-efficiently. Previous studies assume that image-text pairs are given and their category labels are asked to the annotator. However, in the recent ITR studies, the importance of category label is decreased since a retrieval model can be trained with only image-text pairs. For this reason, we set up an active learning scenario where unpaired images (or texts) are given and the annotator provides corresponding texts (or images) to make paired data. The key idea of the proposed AL algorithm is to select unpaired images (or texts) that can be hard negative samples for existing texts (or images). To this end, we introduce a novel scoring function to choose hard negative samples. We validate the effectiveness of the proposed method on Flickr30K and MS-COCO datasets.
format Preprint
id arxiv_https___arxiv_org_abs_2405_16301
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Active Learning for Finely-Categorized Image-Text Retrieval by Selecting Hard Negative Unpaired Samples
Jo, Dae Ung
Lee, Kyuewang
Chung, JaeHo
Choi, Jin Young
Computer Vision and Pattern Recognition
Machine Learning
Securing a sufficient amount of paired data is important to train an image-text retrieval (ITR) model, but collecting paired data is very expensive. To address this issue, in this paper, we propose an active learning algorithm for ITR that can collect paired data cost-efficiently. Previous studies assume that image-text pairs are given and their category labels are asked to the annotator. However, in the recent ITR studies, the importance of category label is decreased since a retrieval model can be trained with only image-text pairs. For this reason, we set up an active learning scenario where unpaired images (or texts) are given and the annotator provides corresponding texts (or images) to make paired data. The key idea of the proposed AL algorithm is to select unpaired images (or texts) that can be hard negative samples for existing texts (or images). To this end, we introduce a novel scoring function to choose hard negative samples. We validate the effectiveness of the proposed method on Flickr30K and MS-COCO datasets.
title Active Learning for Finely-Categorized Image-Text Retrieval by Selecting Hard Negative Unpaired Samples
topic Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2405.16301