Transformer Based Multi-Grained Features for Unsupervised Person Re-Identification
Multi-grained features extracted from convolutional neural networks (CNNs) have demonstrated their strong discrimination ability in supervised person re-identification (Re-ID) tasks. Inspired by them, this work investigates the way of extracting multi-grained features from a pure transformer network to address the unsupervised Re-ID problem that is label-free but much more challenging. To this end, we build a dual-branch network architecture based upon a modified Vision Transformer (ViT). The local tokens output in each branch are reshaped and then uniformly partitioned into multiple stripes to generate part-level features, while the global tokens of two branches are averaged to produce a global feature. Further, based upon offline-online associated camera-aware proxies (O2CAP) that is a top-performing unsupervised Re-ID method, we define offline and online contrastive learning losses with respect to both global and part-level features to conduct unsupervised learning. Extensive experiments on three person Re-ID datasets show that the proposed method outperforms state-of-the-art unsupervised methods by a considerable margin, greatly mitigating the gap to supervised counterparts. Code will be available soon at https://github.com/RikoLi/WACV23-workshop-TMGF.
Code (1)
Tasks
Contrastive LearningPerson Re-IdentificationUnsupervised Person Re-IdentificationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
PersonViT: Large-scale Self-supervised Vision Transformer for Person Re-Identification
Person Re-Identification (ReID) aims to retrieve relevant individuals in non-overlapping camera images and has a wide range of applications in the field of public safety. In recent years, with the development of Vision T…
Contrastive LearningPerson Re-IdentificationSelf-Supervised LearningUnsupervised Pre-trainingLearning Feature Fusion for Unsupervised Domain Adaptive Person Re-identification
Unsupervised domain adaptive (UDA) person re-identification (ReID) has gained increasing attention for its effectiveness on the target domain without manual annotations. Most fine-tuning based UDA person ReID methods foc…
Unsupervised Domain AdaptationUnsupervised Domain AdaptationnUnsupervised Domain Adaptation on Duke to MarketUnsupervised Domain Adaptation on Market to DukeUnleashing Potential of Unsupervised Pre-Training With Intra-Identity Regularization for Person Re-Identification
Existing person re-identification (ReID) methods typically directly load the pre-trained ImageNet weights for initialization. However, as a fine-grained classification task, ReID is more challenging and exists a larg…
Contrastive LearningPerson Re-IdentificationRepresentation LearningUnsupervised Pre-trainingUnleashing the Potential of Unsupervised Pre-Training with Intra-Identity Regularization for Person Re-Identification
Existing person re-identification (ReID) methods typically directly load the pre-trained ImageNet weights for initialization. However, as a fine-grained classification task, ReID is more challenging and exists a large do…
Contrastive LearningPerson Re-IdentificationRepresentation LearningUnsupervised Pre-trainingSequential Transformer for End-to-End Person Search
Person Search aims to simultaneously localize and recognize a target person from realistic and uncropped gallery images. One major challenge of person search comes from the contradictory goals of the two sub-tasks, i.e.,…
Human DetectionPerson Re-IdentificationPerson Search