Fully Unsupervised Person Re-identification Viaselective Contrastive Learning

Abstract

Person re-identification (ReID) aims at searching the same identity person among images captured by various cameras. Unsupervised person ReID attracts a lot of attention recently, due to it works without intensive manual annotation and thus shows great potential of adapting to new conditions. Representation learning plays a critical role in unsupervised person ReID. In this work, we propose a novel selective contrastive learning framework for unsupervised feature learning. Specifically, different from traditional contrastive learning strategies, we propose to use multiple positives and adaptively sampled negatives for defining the contrastive loss, enabling to learn a feature embedding model with stronger identity discriminative representation. Moreover, we propose to jointly leverage global and local features to construct three dynamic dictionaries, among which the global and local memory banks are used for pairwise similarity computation and the mixture memory bank are used for contr

Stats

• citations20
• S2 citations—
• github stars0
• HF likes0
• heat score9.92
• arxiv keypang2020fully

Related papers

• A Discriminatively Learned CNN Embedding For Person Re-identification (2016)20.32
• Deep Co-attention Based Comparators For Relative Representation Learning In Person Re-identification (2018)13.34
• Deep-person: Learning Discriminative Deep Features For Person Re-identification (2017)16.90
• Implicit Discriminative Knowledge Learning For Visible-infrared Person Re-identification (2024)16.19
• Cross-entropy Adversarial View Adaptation For Person Re-identification (2019)12.93
• Triplet-based Deep Similarity Learning For Person Re-identification (2018)10.61
• A Pose-sensitive Embedding For Person Re-identification With Expanded Cross Neighborhood Re-ranking (2017)23.25
• Advancing Person Re-identification: Tensor-based Feature Fusion And Multilinear Subspace Learning (2023)2.26