Domain Generalized Person Re-Identification via Cross-Domain Episodic Learning
Aiming at recognizing images of the same person across distinct camera views, person re-identification (re-ID) has been among active research topics in computer vision. Most existing re-ID works require collection of a large amount of labeled image data from the scenes of interest. When the data to be recognized are different from the source-domain training ones, a number of domain adaptation approaches have been proposed. Nevertheless, one still needs to collect labeled or unlabelled target-domain data during training. In this paper, we tackle an even more challenging and practical setting, domain generalized (DG) person re-ID. That is, while a number of labeled source-domain datasets are available, we do not have access to any target-domain training data. In order to learn domain-invariant features without knowing the target domain of interest, we present an episodic learning scheme which advances meta learning strategies to exploit the observed source-domain labeled data. The learned features would exhibit sufficient domain-invariant properties while not overfitting the source-domain data or ID labels. Our experiments on four benchmark datasets confirm the superiority of our method over the state-of-the-arts.
Code (0)
등록된 구현이 없습니다.
Tasks
Domain AdaptationDomain GeneralizationGeneralizable Person Re-identificationMeta-LearningPerson Re-IdentificationSimilar Papers 제목 키워드 기반
Aligned Divergent Pathways for Omni-Domain Generalized Person Re-Identification
Person Re-identification (Person ReID) has advanced significantly in fully supervised and domain generalized Person R e ID. However, methods developed for one task domain transfer poorly to the other. An ideal Person ReI…
Domain GeneralizationPerson Re-IdentificationSingle-Source Domain GeneralizationA Unified Deep Semantic Expansion Framework for Domain-Generalized Person Re-identification
Supervised Person Re-identification (Person ReID) methods have achieved excellent performance when training and testing within one camera network. However, they usually suffer from considerable performance degradation wh…
Domain AdaptationImage RetrievalPerson Re-IdentificationDiverse Deep Feature Ensemble Learning for Omni-Domain Generalized Person Re-identification
Person Re-identification (Person ReID) has progressed to a level where single-domain supervised Person ReID performance has saturated. However, such methods experience a significant drop in performance when trained and t…
Domain GeneralizationEnsemble LearningPerson Re-IdentificationMulti-Domain Adversarial Feature Generalization for Person Re-Identification
With the assistance of sophisticated training methods applied to single labeled datasets, the performance of fully-supervised person re-identification (Person Re-ID) has been improved significantly in recent years. Howev…
Domain AdaptationDomain GeneralizationPerson Re-IdentificationUnsupervised Domain AdaptationFederated and Generalized Person Re-identification through Domain and Feature Hallucinating
In this paper, we study the problem of federated domain generalization (FedDG) for person re-identification (re-ID), which aims to learn a generalized model with multiple decentralized labeled source domains. An empirica…
Domain GeneralizationPerson Re-IdentificationUnsupervised Domain Adaptation