AMNS: Attention-weighted Selective Mask And Noise Label Suppression For Text-to-image Person Retrieval

Abstract

Most existing text-to-image person retrieval methods usually assume that the training image-text pairs are perfectly aligned; however, the noisy correspondence(NC) issue (i.e., incorrect or unreliable alignment) exists due to poor image quality and labeling errors. Additionally, random masking augmentation may inadvertently discard critical semantic content, introducing noisy matches between images and text descriptions. To address the above two challenges, we propose a noise label suppression method to mitigate NC and an Attention-Weighted Selective Mask (AWM) strategy to resolve the issues caused by random masking. Specifically, the Bidirectional Similarity Distribution Matching (BSDM) loss enables the model to effectively learn from positive pairs while preventing it from over-relying on them, thereby mitigating the risk of overfitting to noisy labels. In conjunction with this, Weight Adjustment Focal (WAF) loss improves the model's ability to handle hard samples. Furthermore, AWM p

Stats

• citations1
• S2 citations—
• github stars0
• HF likes0
• heat score2.26
• arxiv keyzhang2024amns

Related papers

• Dynamic Uncertainty Learning With Noisy Correspondence For Text-based Person Search (2025)7.50
• Multi-path Exploration And Feedback Adjustment For Text-to-image Person Retrieval (2024)0.00
• Decoupled Cross-modal Alignment Network For Text-rgbt Person Retrieval And A High-quality Benchmark (2025)0.00
• Boosting Weak Positives For Text Based Person Search (2025)0.00
• Hybrid, Unified And Iterative: A Novel Framework For Text-based Person Anomaly Retrieval (2025)0.00
• Cross-modal Implicit Relation Reasoning And Aligning For Text-to-image Person Retrieval (2023)18.15
• CAIBC: Capturing All-round Information Beyond Color For Text-based Person Retrieval (2022)15.37
• MCA: 2D-3D Retrieval With Noisy Labels Via Multi-level Adaptive Correction And Alignment (2025)0.00