Papers › Self-paced Contrastive Learning with Hybrid Memory for Domain Adaptive Object Re-ID

Self-paced Contrastive Learning with Hybrid Memory for Domain Adaptive Object Re-ID

4 Jun 2020NeurIPS 2020 12arXiv:2006.02713archive 2025-07-28

Yixiao Ge, Feng Zhu, Dapeng Chen, Rui Zhao, Hongsheng Li

Domain adaptive object re-ID aims to transfer the learned knowledge from the labeled source domain to the unlabeled target domain to tackle the open-class re-identification problems. Although state-of-the-art pseudo-label-based methods have achieved great success, they did not make full use of all valuable information because of the domain gap and unsatisfying clustering performance. To solve these problems, we propose a novel self-paced contrastive learning framework with hybrid memory. The hybrid memory dynamically generates source-domain class-level, target-domain cluster-level and un-clustered instance-level supervisory signals for learning feature representations. Different from the conventional contrastive learning strategy, the proposed framework jointly distinguishes source-domain classes, and target-domain clusters and un-clustered instances. Most importantly, the proposed self-paced method gradually creates more reliable clusters to refine the hybrid memory and learning targets, and is shown to be the key to our outstanding performance. Our method outperforms state-of-the-arts on multiple domain adaptation tasks of object re-ID and even boosts the performance on the source domain without any extra annotations. Our generalized version on unsupervised object re-ID surpasses state-of-the-art algorithms by considerable 16.7% and 7.9% on Market-1501 and MSMT17 benchmarks.

PaperPDFConference PDFCodeCode Syntology ran

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

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2006.02713")

Code

Syntology Ran 3 of 5 code samples harvested from 2 repositories linked to this paper; 2 have no recorded run. Of those that ran: 1 ran · our draft was wrong; 2 ran with no contract checked.

By repository: official repository: 3 samples from 1 repository, 3 ran; community (archive-listed): 2 samples from 1 repository, 0 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

yxgeee/SpCL officialmentioned in papermentioned on GitHubpytorch report
GJTNB/reading-memo mentioned on GitHubpytorch report
open-mmlab/OpenUnReID mentioned 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

5 samples harvested; 3 ran; 0 honoured the contract we drafted; 2 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

1ran · our draft was wrong
2ran
2unverified

Licence: 0 of the 5 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 2 repositories linked to this paper, official or community; each sample names its own and says which. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

HM yxgeee/SpCL/spcl/models/hm.py official repository ran MIT (permissive) · 198515d7a87b4074 · report
HybridMemory yxgeee/SpCL/spcl/models/hm.py official repository ran · metamorphic tier: deterministic MIT (permissive) · 94a0cbacdd9fae2e · report
hm yxgeee/SpCL/spcl/models/hm.py official repository ran · our draft was wrong MIT (permissive) · 6bee8a7a58df869e · report
HybridMemory open-mmlab/OpenUnReID/openunreid/models/losses/memory.py community (archive-listed) unverified Apache-2.0 (permissive) · 21c9ef17b1caacd1 · report
hm open-mmlab/OpenUnReID/openunreid/models/losses/memory.py community (archive-listed) unverified Apache-2.0 (permissive) · 669dde59f08f64b3 · report

Tasks

ClusteringContrastive LearningDomain AdaptationObjectPseudo LabelUnsupervised Domain AdaptationUnsupervised Person Re-Identification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Unsupervised Domain Adaptation Duke to MSMT SpCL mAP 26.5 #4 of 13 Archive leaderboard report
Unsupervised Domain Adaptation Duke to MSMT SpCL rank-1 53.1 #4 of 13 Archive leaderboard report
Unsupervised Domain Adaptation Duke to MSMT SpCL rank-10 70.5 #4 of 13 Archive leaderboard report
Unsupervised Domain Adaptation Duke to MSMT SpCL rank-5 65.8 #4 of 13 Archive leaderboard report
Unsupervised Domain Adaptation Duke to Market SpCL mAP 76.7 #6 of 26 Archive leaderboard report
Unsupervised Domain Adaptation Duke to Market SpCL rank-1 90.3 #6 of 26 Archive leaderboard report
Unsupervised Domain Adaptation Duke to Market SpCL rank-10 97.7 #6 of 26 Archive leaderboard report
Unsupervised Domain Adaptation Duke to Market SpCL rank-5 96.2 #6 of 26 Archive leaderboard report
Unsupervised Domain Adaptation Market to Duke SpCL mAP 68.8 #6 of 25 Archive leaderboard report
Unsupervised Domain Adaptation Market to Duke SpCL rank-1 82.9 #6 of 25 Archive leaderboard report
Unsupervised Domain Adaptation Market to Duke SpCL rank-10 92.5 #6 of 25 Archive leaderboard report
Unsupervised Domain Adaptation Market to Duke SpCL rank-5 90.1 #6 of 25 Archive leaderboard report
Unsupervised Domain Adaptation Market to MSMT SpCl mAP 25.4 #7 of 17 Archive leaderboard report
Unsupervised Domain Adaptation Market to MSMT SpCl rank-1 51.6 #7 of 17 Archive leaderboard report
Unsupervised Domain Adaptation Market to MSMT SpCl rank-10 69.7 #7 of 17 Archive leaderboard report
Unsupervised Domain Adaptation Market to MSMT SpCl rank-5 64.3 #7 of 17 Archive leaderboard report
Unsupervised Domain Adaptation VehicleID to VERI-Wild Large SPCL R-1 32.7 #9 of 9 Archive leaderboard report
Unsupervised Domain Adaptation VehicleID to VERI-Wild Large SPCL R-10 - #9 of 9 Archive leaderboard report
Unsupervised Domain Adaptation VehicleID to VERI-Wild Large SPCL R-5 55.7 #9 of 9 Archive leaderboard report
Unsupervised Domain Adaptation VehicleID to VERI-Wild Large SPCL mAP 16.6 #9 of 9 Archive leaderboard report
Unsupervised Domain Adaptation VehicleID to VERI-Wild Medium SPCL R-1 42.0 #9 of 9 Archive leaderboard report
Unsupervised Domain Adaptation VehicleID to VERI-Wild Medium SPCL R-10 - #9 of 9 Archive leaderboard report
Unsupervised Domain Adaptation VehicleID to VERI-Wild Medium SPCL R-5 66.1 #9 of 9 Archive leaderboard report
Unsupervised Domain Adaptation VehicleID to VERI-Wild Medium SPCL mAP 21.5 #9 of 9 Archive leaderboard report
Unsupervised Domain Adaptation VehicleID to VERI-Wild Small SPCL R-1 48.8 #8 of 9 Archive leaderboard report
Unsupervised Domain Adaptation VehicleID to VERI-Wild Small SPCL R-10 - #8 of 9 Archive leaderboard report
Unsupervised Domain Adaptation VehicleID to VERI-Wild Small SPCL R-5 72.8 #8 of 9 Archive leaderboard report
Unsupervised Domain Adaptation VehicleID to VERI-Wild Small SPCL mAP 25.1 #8 of 9 Archive leaderboard report
Unsupervised Domain Adaptation VehicleID to VeRi-776 SPCL Rank-1 80.4 #8 of 14 Archive leaderboard report
Unsupervised Domain Adaptation VehicleID to VeRi-776 SPCL Rank-5 86.8 #8 of 14 Archive leaderboard report
Unsupervised Domain Adaptation VehicleID to VeRi-776 SPCL mAP 38.9 #8 of 14 Archive leaderboard report
Unsupervised Person Re-Identification DukeMTMC-reID SpCL MAP 65.3 #8 of 13 Archive leaderboard report
Unsupervised Person Re-Identification DukeMTMC-reID SpCL Rank-1 81.2 #8 of 13 Archive leaderboard report
Unsupervised Person Re-Identification DukeMTMC-reID SpCL Rank-10 92.2 #8 of 13 Archive leaderboard report
Unsupervised Person Re-Identification DukeMTMC-reID SpCL Rank-5 90.3 #8 of 13 Archive leaderboard report
Unsupervised Person Re-Identification Market-1501 SpCL MAP 72.6 #17 of 23 Archive leaderboard report
Unsupervised Person Re-Identification Market-1501 SpCL Rank-1 87.7 #17 of 23 Archive leaderboard report
Unsupervised Person Re-Identification Market-1501 SpCL Rank-10 96.9 #17 of 23 Archive leaderboard report
Unsupervised Person Re-Identification Market-1501 SpCL Rank-5 95.2 #17 of 23 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