{"title":"Breaking Through the Noisy Correspondence: A Robust Model for Image-Text Matching","authors":"Haitao Shi, Meng Liu, Xiaoxuan Mu, Xuemeng Song, Yupeng Hu, Liqiang Nie","doi":"10.1145/3662732","DOIUrl":null,"url":null,"abstract":"<p>Unleashing the power of image-text matching in real-world applications is hampered by noisy correspondence. Manually curating high-quality datasets is expensive and time-consuming, and datasets generated using diffusion models are not adequately well-aligned. The most promising way is to collect image-text pairs from the Internet, but it will inevitably introduce noisy correspondence. To reduce the negative impact of noisy correspondence, we propose a novel model that first transforms the noisy correspondence filtering problem into a similarity distribution modeling problem by exploiting the powerful capabilities of pre-trained models. Specifically, we use the Gaussian Mixture model to model the similarity obtained by CLIP as clean distribution and noisy distribution, to filter out most of the noisy correspondence in the dataset. Afterward, we used relatively clean data to fine-tune the model. To further reduce the negative impact of unfiltered noisy correspondence, i.e., a minimal part where two distributions intersect during the fine-tuning process, we propose a distribution-sensitive dynamic margin ranking loss, further increasing the distance between the two distributions. Through continuous iteration, the noisy correspondence gradually decreases and the model performance gradually improves. Our extensive experiments demonstrate the effectiveness and robustness of our model even under high noise rates.</p>","PeriodicalId":50936,"journal":{"name":"ACM Transactions on Information Systems","volume":null,"pages":null},"PeriodicalIF":5.4000,"publicationDate":"2024-04-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"ACM Transactions on Information Systems","FirstCategoryId":"94","ListUrlMain":"https://doi.org/10.1145/3662732","RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"COMPUTER SCIENCE, INFORMATION SYSTEMS","Score":null,"Total":0}
引用次数: 0
Abstract
Unleashing the power of image-text matching in real-world applications is hampered by noisy correspondence. Manually curating high-quality datasets is expensive and time-consuming, and datasets generated using diffusion models are not adequately well-aligned. The most promising way is to collect image-text pairs from the Internet, but it will inevitably introduce noisy correspondence. To reduce the negative impact of noisy correspondence, we propose a novel model that first transforms the noisy correspondence filtering problem into a similarity distribution modeling problem by exploiting the powerful capabilities of pre-trained models. Specifically, we use the Gaussian Mixture model to model the similarity obtained by CLIP as clean distribution and noisy distribution, to filter out most of the noisy correspondence in the dataset. Afterward, we used relatively clean data to fine-tune the model. To further reduce the negative impact of unfiltered noisy correspondence, i.e., a minimal part where two distributions intersect during the fine-tuning process, we propose a distribution-sensitive dynamic margin ranking loss, further increasing the distance between the two distributions. Through continuous iteration, the noisy correspondence gradually decreases and the model performance gradually improves. Our extensive experiments demonstrate the effectiveness and robustness of our model even under high noise rates.
期刊介绍:
The ACM Transactions on Information Systems (TOIS) publishes papers on information retrieval (such as search engines, recommender systems) that contain:
new principled information retrieval models or algorithms with sound empirical validation;
observational, experimental and/or theoretical studies yielding new insights into information retrieval or information seeking;
accounts of applications of existing information retrieval techniques that shed light on the strengths and weaknesses of the techniques;
formalization of new information retrieval or information seeking tasks and of methods for evaluating the performance on those tasks;
development of content (text, image, speech, video, etc) analysis methods to support information retrieval and information seeking;
development of computational models of user information preferences and interaction behaviors;
creation and analysis of evaluation methodologies for information retrieval and information seeking; or
surveys of existing work that propose a significant synthesis.
The information retrieval scope of ACM Transactions on Information Systems (TOIS) appeals to industry practitioners for its wealth of creative ideas, and to academic researchers for its descriptions of their colleagues'' work.