Papers › Self-similarity Grouping: A Simple Unsupervised Cross Domain Adaptation Approach for...

Self-similarity Grouping: A Simple Unsupervised Cross Domain Adaptation Approach for Person Re-identification

26 Nov 2018ICCV 2019 10arXiv:1811.10144archive 2025-07-28

Yang Fu, Yunchao Wei, Guanshuo Wang, Yuqian Zhou, Honghui Shi, Thomas Huang

Domain adaptation in person re-identification (re-ID) has always been a challenging task. In this work, we explore how to harness the natural similar characteristics existing in the samples from the target domain for learning to conduct person re-ID in an unsupervised manner. Concretely, we propose a Self-similarity Grouping (SSG) approach, which exploits the potential similarity (from global body to local parts) of unlabeled samples to automatically build multiple clusters from different views. These independent clusters are then assigned with labels, which serve as the pseudo identities to supervise the training process. We repeatedly and alternatively conduct such a grouping and training process until the model is stable. Despite the apparent simplify, our SSG outperforms the state-of-the-arts by more than 4.6% (DukeMTMC to Market1501) and 4.4% (Market1501 to DukeMTMC) in mAP, respectively. Upon our SSG, we further introduce a clustering-guided semisupervised approach named SSG ++ to conduct the one-shot domain adaption in an open set setting (i.e. the number of independent identities from the target domain is unknown). Without spending much effort on labeling, our SSG ++ can further promote the mAP upon SSG by 10.7% and 6.9%, respectively. Our Code is available at: https://github.com/OasisYang/SSG .

PaperPDFConference PDFCode

Code

OasisYang/SSG officialmentioned in papermentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

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

Tasks

ClusteringDomain AdaptationOne-Shot LearningPerson Re-IdentificationUnsupervised Domain AdaptationUnsupervised Person Re-Identification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Unsupervised Domain Adaptation Duke to MSMT SSG mAP 13.3 #9 of 13 Archive leaderboard report
Unsupervised Domain Adaptation Duke to MSMT SSG rank-1 32.2 #9 of 13 Archive leaderboard report
Unsupervised Domain Adaptation Duke to MSMT SSG rank-10 51.2 #9 of 13 Archive leaderboard report
Unsupervised Domain Adaptation Duke to MSMT SSG rank-5 - #9 of 13 Archive leaderboard report
Unsupervised Domain Adaptation Duke to Market SSG mAP 58.3 #14 of 26 Archive leaderboard report
Unsupervised Domain Adaptation Duke to Market SSG rank-1 80.0 #14 of 26 Archive leaderboard report
Unsupervised Domain Adaptation Duke to Market SSG rank-10 92.4 #14 of 26 Archive leaderboard report
Unsupervised Domain Adaptation Duke to Market SSG rank-5 90.0 #14 of 26 Archive leaderboard report
Unsupervised Domain Adaptation Market to Duke SSG mAP 53.4 #14 of 25 Archive leaderboard report
Unsupervised Domain Adaptation Market to Duke SSG rank-1 73.0 #14 of 25 Archive leaderboard report
Unsupervised Domain Adaptation Market to Duke SSG rank-10 83.2 #14 of 25 Archive leaderboard report
Unsupervised Domain Adaptation Market to Duke SSG rank-5 80.6 #14 of 25 Archive leaderboard report
Unsupervised Domain Adaptation Market to MSMT SSG mAP 13.2 #13 of 17 Archive leaderboard report
Unsupervised Domain Adaptation Market to MSMT SSG rank-1 31.6 #13 of 17 Archive leaderboard report
Unsupervised Domain Adaptation Market to MSMT SSG rank-10 49.6 #13 of 17 Archive leaderboard report
Unsupervised Domain Adaptation Market to MSMT SSG rank-5 - #13 of 17 Archive leaderboard report
Unsupervised Person Re-Identification DukeMTMC-reID Self-Similarity Grouping (one shot) MAP 55.9 #9 of 13 Archive leaderboard report
Unsupervised Person Re-Identification DukeMTMC-reID Self-Similarity Grouping (one shot) Rank-1 72.4 #9 of 13 Archive leaderboard report
Unsupervised Person Re-Identification DukeMTMC-reID Self-Similarity Grouping (one shot) Rank-10 87.7 #9 of 13 Archive leaderboard report
Unsupervised Person Re-Identification DukeMTMC-reID Self-Similarity Grouping (one shot) Rank-5 84 #9 of 13 Archive leaderboard report
Unsupervised Person Re-Identification DukeMTMC-reID->MSMT17 Self-Similarity Grouping (one shot) Rank-1 43.6 #3 of 7 Archive leaderboard report
Unsupervised Person Re-Identification DukeMTMC-reID->MSMT17 Self-Similarity Grouping (one shot) Rank-10 61.8 #3 of 7 Archive leaderboard report
Unsupervised Person Re-Identification DukeMTMC-reID->MSMT17 Self-Similarity Grouping (one shot) mAP 23.6 #3 of 7 Archive leaderboard report
Unsupervised Person Re-Identification Market-1501 Self-Similarity Grouping (one shot) MAP 71.5 #18 of 23 Archive leaderboard report
Unsupervised Person Re-Identification Market-1501 Self-Similarity Grouping (one shot) Rank-1 87.5 #18 of 23 Archive leaderboard report
Unsupervised Person Re-Identification Market-1501 Self-Similarity Grouping (one shot) Rank-10 96.8 #18 of 23 Archive leaderboard report
Unsupervised Person Re-Identification Market-1501 Self-Similarity Grouping (one shot) Rank-5 95.2 #18 of 23 Archive leaderboard report
Unsupervised Person Re-Identification Market-1501->MSMT17 Self-Similarity Grouping (one shot) Rank-1 27.6 #4 of 7 Archive leaderboard report
Unsupervised Person Re-Identification Market-1501->MSMT17 Self-Similarity Grouping (one shot) Rank-10 45.7 #4 of 7 Archive leaderboard report
Unsupervised Person Re-Identification Market-1501->MSMT17 Self-Similarity Grouping (one shot) mAP 11.8 #4 of 7 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