Clothes-Invariant Feature Learning by Causal Intervention for Clothes-Changing Person Re-identification
Clothes-invariant feature extraction is critical to the clothes-changing person re-identification (CC-ReID). It can provide discriminative identity features and eliminate the negative effects caused by the confounder--clothing changes. But we argue that there exists a strong spurious correlation between clothes and human identity, that restricts the common likelihood-based ReID method P(Y|X) to extract clothes-irrelevant features. In this paper, we propose a new Causal Clothes-Invariant Learning (CCIL) method to achieve clothes-invariant feature learning by modeling causal intervention P(Y|do(X)). This new causality-based model is inherently invariant to the confounder in the causal view, which can achieve the clothes-invariant features and avoid the barrier faced by the likelihood-based methods. Extensive experiments on three CC-ReID benchmarks, including PRCC, LTCC, and VC-Clothes, demonstrate the effectiveness of our approach, which achieves a new state of the art.
Code (0)
등록된 구현이 없습니다.
Tasks
Clothes Changing Person Re-IdentificationPerson Re-IdentificationSimilar Papers 제목 키워드 기반
Learning Domain Invariant Representations for Generalizable Person Re-Identification
Generalizable person Re-Identification (ReID) has attracted growing attention in recent computer vision community. In this work, we construct a structural causal model among identity labels, identity-specific factors (cl…
Data AugmentationDomain GeneralizationGeneralizable Person Re-identificationPerson Re-Identification+1CLIP-Driven Cloth-Agnostic Feature Learning for Cloth-Changing Person Re-Identification
Contrastive Language-Image Pre-Training (CLIP) has shown impressive performance in short-term Person Re-Identification (ReID) due to its ability to extract high-level semantic features of pedestrians, yet its direct appl…
Cloth-Changing Person Re-IdentificationPerson Re-IdentificationApparel-invariant Feature Learning for Apparel-changed Person Re-identification
With the rise of deep learning methods, person Re-Identification (ReID) performance has been improved tremendously in many public datasets. However, most public ReID datasets are collected in a short time window in which…
Person Re-IdentificationRepresentation LearningClothes-Changing Person Re-Identification with Feasibility-Aware Intermediary Matching
Current clothes-changing person re-identification (re-id) approaches usually perform retrieval based on clothes-irrelevant features, while neglecting the potential of clothes-relevant features. However, we observe that r…
Clothes Changing Person Re-IdentificationPerson Re-IdentificationRetrievalCOCAS: A Large-Scale Clothes Changing Person Dataset for Re-identification
Recent years have witnessed great progress in person re-identification (re-id). Several academic benchmarks such as Market1501, CUHK03 and DukeMTMC play important roles to promote the re-id research. To our best knowledg…
Person Re-Identification