Unsupervised Domain Adaptation on Person Re-Identification via Dual-level Asymmetric Mutual Learning
Unsupervised domain adaptation person re-identification (Re-ID) aims to identify pedestrian images within an unlabeled target domain with an auxiliary labeled source-domain dataset. Many existing works attempt to recover reliable identity information by considering multiple homogeneous networks. And take these generated labels to train the model in the target domain. However, these homogeneous networks identify people in approximate subspaces and equally exchange their knowledge with others or their mean net to improve their ability, inevitably limiting the scope of available knowledge and putting them into the same mistake. This paper proposes a Dual-level Asymmetric Mutual Learning method (DAML) to learn discriminative representations from a broader knowledge scope with diverse embedding spaces. Specifically, two heterogeneous networks mutually learn knowledge from asymmetric subspaces through the pseudo label generation in a hard distillation manner. The knowledge transfer between two networks is based on an asymmetric mutual learning manner. The teacher network learns to identify both the target and source domain while adapting to the target domain distribution based on the knowledge of the student. Meanwhile, the student network is trained on the target dataset and employs the ground-truth label through the knowledge of the teacher. Extensive experiments in Market-1501, CUHK-SYSU, and MSMT17 public datasets verified the superiority of DAML over state-of-the-arts.
Code (0)
등록된 구현이 없습니다.
Tasks
Domain AdaptationPerson Re-IdentificationPseudo LabelTransfer LearningUnsupervised Domain AdaptationSimilar Papers 제목 키워드 기반
Anti-Forgetting Adaptation for Unsupervised Person Re-identification
Regular unsupervised domain adaptive person re-identification (ReID) focuses on adapting a model from a source domain to a fixed target domain. However, an adapted ReID model can hardly retain previously-acquired knowled…
Domain Adaptive Person Re-IdentificationPerson Re-IdentificationUnsupervised Person Re-IdentificationUnsupervised Domain Adaptation in Person re-ID via k-Reciprocal Clustering and Large-Scale Heterogeneous Environment Synthesis
An ongoing major challenge in computer vision is the task of person re-identification, where the goal is to match individuals across different, non-overlapping camera views. While recent success has been achieved via sup…
ClusteringDomain AdaptationPerson Re-IdentificationPseudo Label+1Real-Time Online Unsupervised Domain Adaptation for Real-World Person Re-identification
Following the popularity of Unsupervised Domain Adaptation (UDA) in person re-identification, the recently proposed setting of Online Unsupervised Domain Adaptation (OUDA) attempts to bridge the gap towards practical app…
Domain AdaptationOnline unsupervised domain adaptationPerson Re-IdentificationUnsupervised Domain AdaptationDomain-Shared Learning and Gradual Alignment for Unsupervised Domain Adaptation Visible-Infrared Person Re-Identification
Recently, Visible-Infrared person Re-Identification (VI-ReID) has achieved remarkable performance on public datasets. However, due to the discrepancies between public datasets and real-world data, most existing VI-ReID a…
Unsupervised Domain AdaptationPerson Re-IdentificationOnline Unsupervised Domain Adaptation for Person Re-identification
Unsupervised domain adaptation for person re-identification (Person Re-ID) is the task of transferring the learned knowledge on the labeled source domain to the unlabeled target domain. Most of the recent papers that add…
Domain AdaptationOnline unsupervised domain adaptationPerson Re-IdentificationUnsupervised Domain Adaptation