Noisy Correspondence Learning With Meta Similarity Correction

Abstract

Despite the success of multimodal learning in cross-modal retrieval task, the remarkable progress relies on the correct correspondence among multimedia data. However, collecting such ideal data is expensive and time-consuming. In practice, most widely used datasets are harvested from the Internet and inevitably contain mismatched pairs. Training on such noisy correspondence datasets causes performance degradation because the cross-modal retrieval methods can wrongly enforce the mismatched data to be similar. To tackle this problem, we propose a Meta Similarity Correction Network (MSCN) to provide reliable similarity scores. We view a binary classification task as the meta-process that encourages the MSCN to learn discrimination from positive and negative meta-data. To further alleviate the influence of noise, we design an effective data purification strategy using meta-data as prior knowledge to remove the noisy samples. Extensive experiments are conducted to demonstrate the strengths

Stats

• citations35
• S2 citations—
• github stars0
• HF likes0
• heat score11.67
• arxiv keyhan2023noisy

Related papers

• Noisy Correspondence Learning With Self-reinforcing Errors Mitigation (2023)8.09
• Disentangled Noisy Correspondence Learning (2024)3.58
• PCSR: Pseudo-label Consistency-guided Sample Refinement For Noisy Correspondence Learning (2025)0.00
• Adversarial Cross-modal Retrieval Via Learning And Transferring Single-modal Similarities (2019)8.60
• PC\(^2\): Pseudo-classification Based Pseudo-captioning For Noisy Correspondence Learning In Cross-modal Retrieval (2024)9.23
• Learning To Rematch Mismatched Pairs For Robust Cross-modal Retrieval (2024)13.82
• Neighbor-aware Instance Refining With Noisy Labels For Cross-modal Retrieval (2025)2.26
• Self-supervised Video Representation Learning With Meta-contrastive Network (2021)11.85