Confidence guided label refinement improves cross domain person identification
Confidence-Guided Pseudo-Label Refinement for Unsupervised Cross-Domain Person Re-Identification
Computer Vision and Pattern Recognition
Summary
Person re-identification means recognizing the same person in different camera views, which is hard when cameras or locations change. The authors propose a method called CGPLR that improves learning by carefully deciding which guessed labels to trust and which to fix or ignore. CGPLR uses several clues about how reliable each guess is, avoiding mistakes that happen when wrong guesses reinforce themselves. This helps a computer better match people across different camera systems without needing labeled examples in each new setting.
What this means in practice
- •For security system developers: Improve person re-identification accuracy in surveillance systems when deploying in new environments without labeled data.
- •For retail analytics teams: Enhance customer tracking across different store camera setups by refining identity assignments with confidence measures.
Authors
Sundas Iqbal, Danish Ali, Qing Tian, Yuhui Zheng, Jianping Gou, Weihua Ou
Abstract
Unsupervised cross-domain person re-identification remains challenging because domain shifts generate noisy pseudo labels that are reinforced during iterative adaptation. Existing clustering-based methods often rely on limited reliability cues or global confidence criteria and may impose hard identity supervision on ambiguous target samples. To address these limitations, we propose CGPLR, a confidence-guided pseudo-label refinement framework for unsupervised domain-adaptive person re-identification. CGPLR estimates sample-level reliability by jointly modeling centroid compatibility, local neighborhood consistency, separation from the strongest competing cluster and temporal assignment stability. The resulting confidence distribution is used to derive cluster-adaptive upper and lower thresholds for a three-way selective decision. Reliable assignments are preserved, recoverable samples are reassigned only when an alternative cluster receives sufficient geometric and neighborhood support and highly ambiguous samples are deferred from hard identity supervision. The learning objective adapts to these decisions through confidence-weighted supervision for preserved samples, cautious corrected-label weighting for reassigned samples and label-free representation consistency for deferred samples. CGPLR achieves 76.4% Rank-1 accuracy and 47.6% mean average precision (mAP) on Market-1501 to MSMT17, and 95.1% Rank-1 accuracy and 87.7% mAP on MSMT17 to Market-1501, demonstrating effective reliability-aware selective adaptation. The code is available at https://github.com/Sundas058/CGPLR.