Structural-Semantic Reciprocal Learning for Unsupervised Visible-Infrared Person Re-Identification
2026-07-16 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors address the problem of matching people across visible and infrared images without labeled data, which is hard because the two types of images look very different. They propose a method called Structural-Semantic Reciprocal Learning (SSRL) that improves matching by using detailed body parts to get better spatial information and a feedback loop to clean up noisy labels during training. This approach helps the system learn more accurate representations of people across different image types. Their experiments show SSRL performs well compared to existing methods, even beating some that use labeled data.
Visible-Infrared Person Re-IdentificationUnsupervised LearningModality GapPseudo-labelingClusteringBody-part RepresentationSemantic PrototypesClosed-loop FeedbackCross-modal MatchingSYSU-MM01RegDB
Authors
Moyao Tian, Shijia Liu, Yan Yang, Xin Yuan, Minshi Chen, Wei Wang, Xiao Wang
Abstract
Unsupervised visible-infrared person re-identification (USVI-ReID) is challenging due to the large modality gap and the lack of cross-modal identity annotations. Progressive association paradigms have been proposed to gradually bridge the gap, but they suffer from two critical bottlenecks: reliance on ambiguous global representations and unchecked propagation of pseudo-label noise in an open-loop manner. To address these issues, we propose Structural-Semantic Reciprocal Learning (SSRL), a framework that transforms open-loop association into a self-correcting closed-loop system. Structurally, we introduce Fine-grained Structural Decoupling (FSD) to extract discriminative body-part primitives as reliable spatial anchors, complementing ambiguous holistic silhouettes with spatially consistent structural details. Semantically, we design a Closed-loop Semantic Calibration (CSC) mechanism that reconstructs shared semantic prototypes at each epoch and feeds them back into the training loop, effectively filtering pseudo-label noise before the next clustering cycle. Through the reciprocal interaction between structural and semantic learning, SSRL achieves robust cross-modal representation. Extensive experiments demonstrate the competitive performance of SSRL against state-of-the-art USVI-ReID methods on both SYSU-MM01 and RegDB, notably surpassing several supervised counterparts on RegDB.