Papers › Cluster Contrast for Unsupervised Person Re-Identification

Cluster Contrast for Unsupervised Person Re-Identification

22 Mar 2021arXiv:2103.11568archive 2025-07-28

Zuozhuo Dai, Guangyuan Wang, Weihao Yuan, Xiaoli Liu, Siyu Zhu, Ping Tan

State-of-the-art unsupervised re-ID methods train the neural networks using a memory-based non-parametric softmax loss. Instance feature vectors stored in memory are assigned pseudo-labels by clustering and updated at instance level. However, the varying cluster sizes leads to inconsistency in the updating progress of each cluster. To solve this problem, we present Cluster Contrast which stores feature vectors and computes contrast loss at the cluster level. Our approach employs a unique cluster representation to describe each cluster, resulting in a cluster-level memory dictionary. In this way, the consistency of clustering can be effectively maintained throughout the pipline and the GPU memory consumption can be significantly reduced. Thus, our method can solve the problem of cluster inconsistency and be applicable to larger data sets. In addition, we adopt different clustering algorithms to demonstrate the robustness and generalization of our framework. The application of Cluster Contrast to a standard unsupervised re-ID pipeline achieves considerable improvements of 9.9%, 8.3%, 12.1% compared to state-of-the-art purely unsupervised re-ID methods and 5.5%, 4.8%, 4.4% mAP compared to the state-of-the-art unsupervised domain adaptation re-ID methods on the Market, Duke, and MSMT17 datasets. Code is available at https://github.com/alibaba/cluster-contrast.

PaperPDFCodeCode 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="2103.11568")

Code

Syntology Ran 7 of 14 code samples harvested from 2 repositories linked to this paper; 7 have no recorded run. Of those that ran: 1 ran · honoured contract; 2 ran · our draft was wrong; 4 ran with no contract checked.

By repository: official repository: 12 samples from 1 repository, 5 ran; community (archive-listed): 2 samples from 1 repository, 2 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

alibaba/cluster-contrast officialmentioned in papermentioned on GitHubpytorchMIT report
wangguangyuan/ClusterContrast officialmentioned in papermentioned on GitHubpytorch report
2020132075/conmae mentioned on GitHubpytorch report
alibaba/cluster-contrast-reid mentioned on GitHubpytorchMIT 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

14 samples harvested; 7 ran; 1 honoured the contract we drafted; 7 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 · honoured contract
2ran · our draft was wrong
4ran
7unverified

Licence: 0 of the 14 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.

cm alibaba/cluster-contrast/clustercontrast/models/cm.py official repository ran MIT (permissive) · 10ba7332fd4a54eb · report
conv3x3 alibaba/cluster-contrast/clustercontrast/models/resnet_ibn_a.py official repository ran · our draft was wrong MIT (permissive) · fac5364e2f53c6db · report
process_dir alibaba/cluster-contrast/clustercontrast/datasets/dukemtmcreid.py official repository ran MIT (permissive) · 7e822f939fbe184f · report
resnet101_ibn_a alibaba/cluster-contrast/clustercontrast/models/resnet_ibn_a.py official repository ran MIT (permissive) · c7f5d45660e6ec13 · report
resnet50_ibn_a alibaba/cluster-contrast/clustercontrast/models/resnet_ibn_a.py official repository ran MIT (permissive) · 93cbdbc352d644d9 · report
build_pooling_layer alibaba/cluster-contrast/clustercontrast/models/pooling.py official repository unverified MIT (permissive) · 5c5d2f6f3c01ba6c · report
cm_hard alibaba/cluster-contrast/clustercontrast/models/cm.py official repository unverified MIT (permissive) · f2fd62d39c9658d0 · report
extract_cnn_feature alibaba/cluster-contrast/clustercontrast/evaluators.py official repository unverified MIT (permissive) · fbb5efeed7ebfd09 · report
extract_features alibaba/cluster-contrast/clustercontrast/evaluators.py official repository unverified MIT (permissive) · 962810c012a60817 · report
l2norm alibaba/cluster-contrast/clustercontrast/utils/infomap_cluster.py official repository unverified MIT (permissive) · 34b0da41b1dd21f0 · report
label_generator_kmeans alibaba/cluster-contrast/clustercontrast/models/kmeans.py official repository unverified MIT (permissive) · 4560dc753fea5981 · report
pairwise_distance alibaba/cluster-contrast/clustercontrast/evaluators.py official repository unverified MIT (permissive) · b6d5887f94b1db25 · report
intdict2ndarray alibaba/cluster-contrast-reid/clustercontrast/utils/infomap_cluster.py community (archive-listed) ran · honoured contract MIT (permissive) · aa57815e101e6fa5 · report
read_meta alibaba/cluster-contrast-reid/clustercontrast/utils/infomap_cluster.py community (archive-listed) ran · our draft was wrong MIT (permissive) · b91ea1291400178a · report

Tasks

ClusteringDomain AdaptationPerson Re-IdentificationUnsupervised Domain AdaptationUnsupervised Person Re-IdentificationVehicle Re-Identification

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Unsupervised Person Re-Identification MSMT17 Cluster Contrast Rank-1 62 #10 of 12 Archive leaderboard report
Unsupervised Person Re-Identification MSMT17 Cluster Contrast Rank-10 76.7 #10 of 12 Archive leaderboard report
Unsupervised Person Re-Identification MSMT17 Cluster Contrast Rank-5 71.8 #10 of 12 Archive leaderboard report
Unsupervised Person Re-Identification MSMT17 Cluster Contrast mAP 33 #10 of 12 Archive leaderboard report
Unsupervised Person Re-Identification Market-1501 Cluster Contrast MAP 83 #10 of 23 Archive leaderboard report
Unsupervised Person Re-Identification Market-1501 Cluster Contrast Rank-1 92.9 #10 of 23 Archive leaderboard report
Unsupervised Person Re-Identification Market-1501 Cluster Contrast Rank-10 98 #10 of 23 Archive leaderboard report
Unsupervised Person Re-Identification Market-1501 Cluster Contrast Rank-5 97.2 #10 of 23 Archive leaderboard report
Unsupervised Person Re-Identification PersonX Cluster Contrast Rank-1 94.4 #1 of 1 Archive leaderboard report
Unsupervised Person Re-Identification PersonX Cluster Contrast Rank-5 99.3 #1 of 1 Archive leaderboard report
Unsupervised Person Re-Identification PersonX Cluster Contrast mAP 84.7 #1 of 1 Archive leaderboard report
Vehicle Re-Identification VeRi-776 Cluster Contrast Rank-10 92.8 #17 of 17 Archive leaderboard report
Vehicle Re-Identification VeRi-776 Cluster Contrast Rank1 86.2 #17 of 17 Archive leaderboard report
Vehicle Re-Identification VeRi-776 Cluster Contrast Rank5 90.5 #17 of 17 Archive leaderboard report
Vehicle Re-Identification VeRi-776 Cluster Contrast mAP 40.8 #17 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.

Methods

Softmax

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