Papers › Cross-Dataset Person Re-Identification via Unsupervised Pose Disentanglement and Adaptation

Cross-Dataset Person Re-Identification via Unsupervised Pose Disentanglement and Adaptation

20 Sep 2019ICCV 2019 10arXiv:1909.09675archive 2025-07-28

Yu-Jhe Li, Ci-Siang Lin, Yan-Bo Lin, Yu-Chiang Frank Wang

Person re-identification (re-ID) aims at recognizing the same person from images taken across different cameras. To address this challenging task, existing re-ID models typically rely on a large amount of labeled training data, which is not practical for real-world applications. To alleviate this limitation, researchers now targets at cross-dataset re-ID which focuses on generalizing the discriminative ability to the unlabeled target domain when given a labeled source domain dataset. To achieve this goal, our proposed Pose Disentanglement and Adaptation Network (PDA-Net) aims at learning deep image representation with pose and domain information properly disentangled. With the learned cross-domain pose invariant feature space, our proposed PDA-Net is able to perform pose disentanglement across domains without supervision in identities, and the resulting features can be applied to cross-dataset re-ID. Both of our qualitative and quantitative results on two benchmark datasets confirm the effectiveness of our approach and its superiority over the state-of-the-art cross-dataset Re-ID approaches.

PaperPDFConference PDF

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

DisentanglementPerson Re-IdentificationUnsupervised Domain Adaptation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Unsupervised Domain Adaptation Duke to Market PDA-Net mAP 47.6 #18 of 26 Archive leaderboard report
Unsupervised Domain Adaptation Duke to Market PDA-Net rank-1 75.2 #18 of 26 Archive leaderboard report
Unsupervised Domain Adaptation Duke to Market PDA-Net rank-10 90.2 #18 of 26 Archive leaderboard report
Unsupervised Domain Adaptation Duke to Market PDA-Net rank-5 86.3 #18 of 26 Archive leaderboard report
Unsupervised Domain Adaptation Market to Duke PDA-Net mAP 45.1 #17 of 25 Archive leaderboard report
Unsupervised Domain Adaptation Market to Duke PDA-Net rank-1 63.2 #17 of 25 Archive leaderboard report
Unsupervised Domain Adaptation Market to Duke PDA-Net rank-10 82.5 #17 of 25 Archive leaderboard report
Unsupervised Domain Adaptation Market to Duke PDA-Net rank-5 77.0 #17 of 25 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections