Mitigating Noisy Correspondence by Geometrical Structure Consistency Learning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhao, Zihua, Chen, Mengxi, Dai, Tianjie, Yao, Jiangchao, han, Bo, Zhang, Ya, Wang, Yanfeng
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929359901687808
author Zhao, Zihua
Chen, Mengxi
Dai, Tianjie
Yao, Jiangchao
han, Bo
Zhang, Ya
Wang, Yanfeng
author_facet Zhao, Zihua
Chen, Mengxi
Dai, Tianjie
Yao, Jiangchao
han, Bo
Zhang, Ya
Wang, Yanfeng
contents Noisy correspondence that refers to mismatches in cross-modal data pairs, is prevalent on human-annotated or web-crawled datasets. Prior approaches to leverage such data mainly consider the application of uni-modal noisy label learning without amending the impact on both cross-modal and intra-modal geometrical structures in multimodal learning. Actually, we find that both structures are effective to discriminate noisy correspondence through structural differences when being well-established. Inspired by this observation, we introduce a Geometrical Structure Consistency (GSC) method to infer the true correspondence. Specifically, GSC ensures the preservation of geometrical structures within and between modalities, allowing for the accurate discrimination of noisy samples based on structural differences. Utilizing these inferred true correspondence labels, GSC refines the learning of geometrical structures by filtering out the noisy samples. Experiments across four cross-modal datasets confirm that GSC effectively identifies noisy samples and significantly outperforms the current leading methods.
format Preprint
id arxiv_https___arxiv_org_abs_2405_16996
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Mitigating Noisy Correspondence by Geometrical Structure Consistency Learning
Zhao, Zihua
Chen, Mengxi
Dai, Tianjie
Yao, Jiangchao
han, Bo
Zhang, Ya
Wang, Yanfeng
Computer Vision and Pattern Recognition
Noisy correspondence that refers to mismatches in cross-modal data pairs, is prevalent on human-annotated or web-crawled datasets. Prior approaches to leverage such data mainly consider the application of uni-modal noisy label learning without amending the impact on both cross-modal and intra-modal geometrical structures in multimodal learning. Actually, we find that both structures are effective to discriminate noisy correspondence through structural differences when being well-established. Inspired by this observation, we introduce a Geometrical Structure Consistency (GSC) method to infer the true correspondence. Specifically, GSC ensures the preservation of geometrical structures within and between modalities, allowing for the accurate discrimination of noisy samples based on structural differences. Utilizing these inferred true correspondence labels, GSC refines the learning of geometrical structures by filtering out the noisy samples. Experiments across four cross-modal datasets confirm that GSC effectively identifies noisy samples and significantly outperforms the current leading methods.
title Mitigating Noisy Correspondence by Geometrical Structure Consistency Learning
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2405.16996