PCSR: Pseudo-label Consistency-guided Sample Refinement For Noisy Correspondence Learning

Abstract

Cross-modal retrieval aims to align different modalities via semantic similarity. However, existing methods often assume that image-text pairs are perfectly aligned, overlooking Noisy Correspondences in real data. These misaligned pairs misguide similarity learning and degrade retrieval performance. Previous methods often rely on coarse-grained categorizations that simply divide data into clean and noisy samples, overlooking the intrinsic diversity within noisy instances. Moreover, they typically apply uniform training strategies regardless of sample characteristics, resulting in suboptimal sample utilization for model optimization. To address the above challenges, we introduce a novel framework, called Pseudo-label Consistency-Guided Sample Refinement (PCSR), which enhances correspondence reliability by explicitly dividing samples based on pseudo-label consistency. Specifically, we first employ a confidence-based estimation to distinguish clean and noisy pairs, then refine the noisy p

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyliu2025pcsr

Related papers

• PC\(^2\): Pseudo-classification Based Pseudo-captioning For Noisy Correspondence Learning In Cross-modal Retrieval (2024)9.23
• Neighbor-aware Instance Refining With Noisy Labels For Cross-modal Retrieval (2025)2.26
• Noisy Correspondence Learning With Self-reinforcing Errors Mitigation (2023)8.09
• Noisy Correspondence Learning With Meta Similarity Correction (2023)11.67
• Disentangled Noisy Correspondence Learning (2024)3.58
• MCA: 2D-3D Retrieval With Noisy Labels Via Multi-level Adaptive Correction And Alignment (2025)0.00
• Tsvc:tripartite Learning With Semantic Variation Consistency For Robust Image-text Retrieval (2025)3.58
• A Unified Optimal Transport Framework For Cross-modal Retrieval With Noisy Labels (2024)5.24