Papers › Learning to Adapt Invariance in Memory for Person Re-identification

Learning to Adapt Invariance in Memory for Person Re-identification

1 Aug 2019arXiv:1908.00485archive 2025-07-28

Zhun Zhong, Liang Zheng, Zhiming Luo, Shaozi Li, Yi Yang

This work considers the problem of unsupervised domain adaptation in person re-identification (re-ID), which aims to transfer knowledge from the source domain to the target domain. Existing methods are primary to reduce the inter-domain shift between the domains, which however usually overlook the relations among target samples. This paper investigates into the intra-domain variations of the target domain and proposes a novel adaptation framework w.r.t. three types of underlying invariance, i.e., Exemplar-Invariance, Camera-Invariance, and Neighborhood-Invariance. Specifically, an exemplar memory is introduced to store features of samples, which can effectively and efficiently enforce the invariance constraints over the global dataset. We further present the Graph-based Positive Prediction (GPP) method to explore reliable neighbors for the target domain, which is built upon the memory and is trained on the source samples. Experiments demonstrate that 1) the three invariance properties are indispensable for effective domain adaptation, 2) the memory plays a key role in implementing invariance learning and improves the performance with limited extra computation cost, 3) GPP could facilitate the invariance learning and thus significantly improves the results, and 4) our approach produces new state-of-the-art adaptation accuracy on three re-ID large-scale benchmarks.

PaperPDF

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

Domain AdaptationPerson Re-IdentificationUnsupervised Domain Adaptation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Unsupervised Domain Adaptation Duke to MSMT ECN++ mAP 16.0 #8 of 13 Archive leaderboard report
Unsupervised Domain Adaptation Duke to MSMT ECN++ rank-1 42.5 #8 of 13 Archive leaderboard report
Unsupervised Domain Adaptation Duke to MSMT ECN++ rank-10 61.5 #8 of 13 Archive leaderboard report
Unsupervised Domain Adaptation Duke to MSMT ECN++ rank-5 55.9 #8 of 13 Archive leaderboard report
Unsupervised Domain Adaptation Duke to Market ECN++ mAP 63.8 #10 of 26 Archive leaderboard report
Unsupervised Domain Adaptation Duke to Market ECN++ rank-1 84.1 #10 of 26 Archive leaderboard report
Unsupervised Domain Adaptation Duke to Market ECN++ rank-10 95.4 #10 of 26 Archive leaderboard report
Unsupervised Domain Adaptation Duke to Market ECN++ rank-5 92.8 #10 of 26 Archive leaderboard report
Unsupervised Domain Adaptation Market to Duke ECN++ mAP 54.4 #11 of 25 Archive leaderboard report
Unsupervised Domain Adaptation Market to Duke ECN++ rank-1 74.0 #11 of 25 Archive leaderboard report
Unsupervised Domain Adaptation Market to Duke ECN++ rank-10 87.4 #11 of 25 Archive leaderboard report
Unsupervised Domain Adaptation Market to Duke ECN++ rank-5 83.7 #11 of 25 Archive leaderboard report
Unsupervised Domain Adaptation Market to MSMT ECN++ mAP 15.2 #11 of 17 Archive leaderboard report
Unsupervised Domain Adaptation Market to MSMT ECN++ rank-1 40.4 #11 of 17 Archive leaderboard report
Unsupervised Domain Adaptation Market to MSMT ECN++ rank-10 58.7 #11 of 17 Archive leaderboard report
Unsupervised Domain Adaptation Market to MSMT ECN++ rank-5 53.1 #11 of 17 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