paper-with-me

Cross-modal retrieval with noisy correspondence

3개 벤치마크 · 논문 20편 · 이 태스크의 논문 보기 →

Benchmarks

COCO-Noisy

결과 51개

Flickr30K-Noisy

결과 48개

CC152K

결과 45개

Most implemented

Papers

ReCon: Enhancing True Correspondence Discrimination through Relation Consistency for Robust Noisy Correspondence Learning

2025-02-27 · CVPR 2025 1 · Quanxing Zha, Xin Liu, Shu-Juan Peng, Yiu-ming Cheung 외

Can we accurately identify the true correspondences from multimodal datasets containing mismatched data pairs? Existing methods primarily emphasize the similarity matching between the representations of objects across mo…

Cross-Modal RetrievalCross-modal retrieval with noisy correspondenceImage-text matchingImage-text Retrieval+1

PC$^2$: Pseudo-Classification Based Pseudo-Captioning for Noisy Correspondence Learning in Cross-Modal Retrieval

2024-08-02

In the realm of cross-modal retrieval, seamlessly integrating diverse modalities within multimedia remains a formidable challenge, especially given the complexities introduced by noisy correspondence learning (NCL). Such…

Cross-modal retrieval with noisy correspondenceImage-text Retrieval

UGNCL: Uncertainty-Guided Noisy Correspondence Learning for Efficient Cross-Modal Matching

2024-07-11 · SIGIR 2024 7 · Quanxing Zha, Xin Liu, Yiu-ming Cheung, Xing Xu 외

Cross-modal matching has recently gained significant popularity to facilitate retrieval across multi-modal data, and existing works are highly relied on an implicit assumption that the training data pairs are perfectly a…

Cross-Modal RetrievalCross-modal retrieval with noisy correspondenceImage-text matchingImage-text Retrieval

Mitigating Noisy Correspondence by Geometrical Structure Consistency Learning

2024-05-27 · CVPR 2024 1 · Zihua Zhao, Mengxi Chen, Tianjie Dai, Jiangchao Yao 외

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…

Cross-modal retrieval with noisy correspondence

Breaking Through the Noisy Correspondence: A Robust Model for Image-Text Matching

2024-04-29 · ACM Transactions on Information Systems 2024 4 · Haitao Shi, Meng Liu, Xiaoxuan Mu, Xuemeng Song 외

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 …

Cross-modal retrieval with noisy correspondenceImage-text matchingText Matching

Learning with Noisy Correspondence

2024-04-13 · International Journal of Computer Vision 2024 4 · Zhenyu Huang, Peng Hu, guocheng niu, Xinyan Xiao 외

This paper studies a new learning paradigm for noisy labels, i.e., noisy correspondence (NC). Unlike the well-studied noisy labels that consider the errors in the category annotation of a sample, the NC refers to the err…

Cross-Modal RetrievalCross-modal retrieval with noisy correspondenceRetrievalText Retrieval+2

전체 20편 보기 →