Mutual Information Guided Optimal Transport for Unsupervised Visible-Infrared Person Re-identification
원문 초록
Unsupervised visible infrared person re-identification (USVI-ReID) is a challenging retrieval task that aims to retrieve cross-modality pedestrian images without using any label information. In this task, the large cross-modality variance makes it difficult to generate reliable cross-modality labels, and the lack of annotations also provides additional difficulties for learning modality-invariant features. In this paper, we first deduce an optimization objective for unsupervised VI-ReID based on the mutual information between the model's cross-modality input and output. With equivalent derivation, three learning principles, i.e., "Sharpness" (entropy minimization), "Fairness" (uniform label distribution), and "Fitness" (reliable cross-modality matching) are obtained. Under their guidance, we design a loop iterative training strategy alternating between model training and cross-modality matching. In the matching stage, a uniform prior guided optimal transport assignment ("Fitness", "Fairness") is proposed to select matched visible and infrared prototypes. In the training stage, we utilize this matching information to introduce prototype-based contrastive learning for minimizing the intra- and cross-modality entropy ("Sharpness"). Extensive experimental results on benchmarks demonstrate the effectiveness of our method, e.g., 60.6% and 90.3% of Rank-1 accuracy on SYSU-MM01 and RegDB without any annotations.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Why Multi-Interest Fairness Matters: Hypergraph Contrastive Multi-Interest Learning for Fair Conversational Recommender System
FairASR: Fair Audio Contrastive Learning for Automatic Speech Recognition
A Unified Framework against Topology and Class Imbalance
A Reproducibility Study of Product-side Fairness in Bundle Recommendation
Try Harder: Hard Sample Generation and Learning for Clothes-Changing Person Re-ID
Fairness-Aware Grouping for Continuous Sensitive Variables: Application for Debiasing Face Analysis with respect to Skin Tone
토론
이 논문과 연결된 포럼 글이 아직 없습니다.