Papers › Joint Discriminative and Generative Learning for Person Re-identification

Joint Discriminative and Generative Learning for Person Re-identification

15 Apr 2019CVPR 2019 6arXiv:1904.07223archive 2025-07-28

Zhedong Zheng, Xiaodong Yang, Zhiding Yu, Liang Zheng, Yi Yang, Jan Kautz

Person re-identification (re-id) remains challenging due to significant intra-class variations across different cameras. Recently, there has been a growing interest in using generative models to augment training data and enhance the invariance to input changes. The generative pipelines in existing methods, however, stay relatively separate from the discriminative re-id learning stages. Accordingly, re-id models are often trained in a straightforward manner on the generated data. In this paper, we seek to improve learned re-id embeddings by better leveraging the generated data. To this end, we propose a joint learning framework that couples re-id learning and data generation end-to-end. Our model involves a generative module that separately encodes each person into an appearance code and a structure code, and a discriminative module that shares the appearance encoder with the generative module. By switching the appearance or structure codes, the generative module is able to generate high-quality cross-id composed images, which are online fed back to the appearance encoder and used to improve the discriminative module. The proposed joint learning framework renders significant improvement over the baseline without using generated data, leading to the state-of-the-art performance on several benchmark datasets.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

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

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 19 code samples harvested from 5 repositories linked to this paper: 12 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 3 where Syntology's instrument failed) · 7 unverified. Where Syntology's instrument failed: 2 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 19 samples from 5 repositories, 12 ran (9 with no instrument failure; 3 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

No sample is linked to this paper from 1 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 1 of the 12 samples that ran has no recorded date.

Demonhesusheng/Reid mentioned on GitHubpytorchMITSyntology: not harvested report
NVlabs/DG-Net mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
Proxim123/person-reID-No1- mentioned on GitHubpytorchMITSyntology: 4 samples, 2 ran (0 instrument-failed) · 2 unverified report
WuRui-Ella/Myfirststore mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
ivychill/reid mentioned on GitHubpytorchMITSyntology: 11 samples, 10 ran (3 instrument-failed) · 1 unverified report
jiangsikai/Person_reID_baseline_pytorch mentioned on GitHubpytorchSyntology: 1 sample, 0 ran · 1 unverified report
layumi/DG-Net mentioned on GitHubpytorchSyntology: not harvested report
layumi/Person_reID_baseline_pytorch mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Swin Transformer: Hierarchical Vision Transformer using Shifted Windows (arXiv:2103.14030; that paper's own run record: 123 ran (of which 45 constructed an object rather than computing a result; 79 with no instrument failure: 6 honoured, 3 violated, 70 with no contract checked; 44 where Syntology's instrument failed) · 84 unverified); nothing checks that they implement this paper's method. report
lsh110600/person_re_id mentioned on GitHubpytorchSyntology: 1 sample, 0 ran · 1 unverified report
taroogura/Person_reID_baseline_pytorch mentioned on GitHubpytorchMITSyntology: 2 samples, 0 ran · 2 unverified report
wxb589/Person_reID_baseline_pytorch-master mentioned on GitHubpytorchMITSyntology: not harvested report
youwenjing/reid_mgn-dgnet mentioned on GitHubpytorchSyntology: not harvested 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

19 samples harvested: 12 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 3 where Syntology's instrument failed) · 7 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

2ran · our draft was wrong
1ran; the contract check could not run
9ran
7unverified

Licence: 2 of the 19 samples are pointer only, meaning Syntology does not serve that copy's text. For 2 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 5 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “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. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (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 are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. 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 six 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; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. 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.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

Proxim123/person-reID-No1- community (archive-listed) 4 samples, 2 ran (0 instrument-failed) · 2 unverified
k_reciprocal_neigh in 6 papers re_ranking.py ran MIT (permissive) · a610e67edff490e6 · report fixture: signature initial_rank:ndarray/2/int, i:int/0/int, k1:int/0/int · returned ndarray · level recorded 2026-09-24
re_ranking in 8 papers re_ranking.py ran MIT (permissive) · 59df0fc45b7bbcca · report fixture: signature q_g_dist:ndarray/2/float, q_q_dist:ndarray/2/float, g_g_dist:ndarray/2/float, k1:int/0/int, k2:int/0/int, lambda_value:float/0/float · returned ndarray · level recorded 2026-09-24
compute_mAP in 9 papers evaluate.py unverified MIT (permissive) · 3f91b09177ddeb33 · report
evaluate in 514 papers evaluate_rerank.py unverified MIT (permissive) · c3d73c7bc76855c8 · report
ivychill/reid community (archive-listed) 11 samples, 10 ran (3 instrument-failed) · 1 unverified
euclidean_dist in 69 papers
census: 12 implementations from 14 papers, 3 distinct outputs on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32 · arg 2: rank 2, kind float, dtype float32
loss.py ran · our draft was wrong fingerprinted MIT (permissive) here; the stored copy is pointer only · c83d9f7fca950b77 · report fixture: signature x:Tensor/2/float, y:Tensor/2/float · returned Tensor · level recorded, date not recorded
eval_func reid_metric.py ran fingerprinted MIT (permissive) · 979f7c2f5bb4a9ec · report fixture: signature distmat:ndarray/2/float, q_pids:ndarray/1/int, g_pids:ndarray/1/int, q_camids:ndarray/1/int, g_camids:ndarray/1/int, max_rank:int/0/int · returned tuple · level recorded 2026-09-24
fliplr in 9 papers evaluate_online.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted MIT (permissive) here; the stored copy is pointer only · e324277ab874fc3a · report fixture: signature img:Tensor/4/float · returned Tensor · level recorded 2026-09-22
getDataFromTxt data_split.py ran MIT (permissive) · c5ee3b062fa991cd · report fixture: signature train_all_txt:str/0/str · returned dict · level recorded 2026-09-24
get_id in 15 papers evaluate_online.py ran MIT (permissive) · 1647e452ac25bf3c · report fixture: signature img_path:list/1/tuple · returned tuple · level recorded 2026-09-24
hard_example_mining in 9 papers loss.py ran MIT (permissive) · 93f2c0b80ea7f36e · report fixture: signature dist_mat:Tensor/2/float, labels:Tensor/1/int, return_inds:bool/0/bool · returned tuple · level recorded 2026-09-25
normalize in 638 papers
census: 70 implementations from 82 papers, 51 distinct outputs across 11 buckets, one shared input per bucket this sample: bucket 1 of 11, arg 1: rank 2, kind float, dtype float32
loss.py ran · our draft was wrong fingerprinted MIT (permissive) · e3b2a83f52101f2d · report fixture: signature x:Tensor/2/float, axis:int/0/int · returned Tensor · level recorded 2026-09-22
read_image in 73 papers dataset_loader.py ran MIT (permissive) · 6cd98fed94c1be75 · report fixture: signature img_path:str/0/str · returned Image · level recorded 2026-09-24
selectDataFromDataDic data_split.py ran MIT (permissive) · 4fb1bffe87902d0a · report fixture: signature inds:list/1/str, data_dic:dict/0/? · returned tuple · level recorded 2026-09-24
splitQueryDataGallayrData data_split.py ran MIT (permissive) · 29539deb062cf054 · report fixture: signature data_all_dic:dict/0/?, skip:int/0/int, max_len:int/0/int, ratios:float/0/float, remain_skip:bool/0/bool · returned tuple · level recorded 2026-09-24
compute_mAP in 9 papers reid_metric.py unverified MIT (permissive) · 5ae586aedc34bdd6 · report
jiangsikai/Person_reID_baseline_pytorch community (archive-listed) 1 sample, 0 ran · 1 unverified
evaluate in 514 papers evaluate.py unverified MIT (permissive) · 3713e246e333c32a · report
lsh110600/person_re_id community (archive-listed) 1 sample, 0 ran · 1 unverified
evaluate in 514 papers evaluate_gpu.py unverified MIT (permissive) · aa35d5d95fb54d49 · report
taroogura/Person_reID_baseline_pytorch community (archive-listed) 2 samples, 0 ran · 2 unverified
evaluate in 514 papers evaluate_gpu.py unverified MIT (permissive) · a87e51760037d9e3 · report
sort_img demo1.py unverified MIT (permissive) · 52efb1cc6b07efc4 · report

Tasks

Image GenerationImage-to-Image TranslationPerson Re-IdentificationUnsupervised Domain AdaptationUnsupervised Person Re-Identification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Person Re-Identification CUHK03 DG-Net MAP 61.1 #13 of 19 Archive leaderboard report
Person Re-Identification CUHK03 DG-Net Rank-1 65.6 #13 of 19 Archive leaderboard report
Person Re-Identification DukeMTMC-reID DG-Net(RK) Rank-1 90.26 #17 of 94 Archive leaderboard report
Person Re-Identification DukeMTMC-reID DG-Net(RK) mAP 88.31 #17 of 94 Archive leaderboard report
Person Re-Identification DukeMTMC-reID DG-Net Rank-1 86.6 #57 of 94 Archive leaderboard report
Person Re-Identification DukeMTMC-reID DG-Net mAP 74.8 #57 of 94 Archive leaderboard report
Person Re-Identification MSMT17 DG-Net Rank-1 77.2 #34 of 43 Archive leaderboard report
Person Re-Identification MSMT17 DG-Net Rank-10 90.5 #34 of 43 Archive leaderboard report
Person Re-Identification MSMT17 DG-Net Rank-5 87.4 #34 of 43 Archive leaderboard report
Person Re-Identification MSMT17 DG-Net mAP 52.3 #34 of 43 Archive leaderboard report
Person Re-Identification Market-1501 DG-Net(RK) Rank-1 95.4 #60 of 135 Archive leaderboard report
Person Re-Identification Market-1501 DG-Net(RK) mAP 92.49 #60 of 135 Archive leaderboard report
Person Re-Identification Market-1501 DG-Net Rank-1 94.8 #73 of 135 Archive leaderboard report
Person Re-Identification Market-1501 DG-Net mAP 86.0 #73 of 135 Archive leaderboard report
Person Re-Identification Market-1501-C DG-Net Rank-1 31.75 #11 of 22 Archive leaderboard report
Person Re-Identification Market-1501-C DG-Net mAP 9.96 #11 of 22 Archive leaderboard report
Person Re-Identification Market-1501-C DG-Net mINP 0.35 #11 of 22 Archive leaderboard report
Person Re-Identification UAV-Human DG-Net Rank-1 65.81 #1 of 4 Archive leaderboard report
Person Re-Identification UAV-Human DG-Net Rank-5 85.71 #1 of 4 Archive leaderboard report
Person Re-Identification UAV-Human DG-Net mAP 61.97 #1 of 4 Archive leaderboard report
Unsupervised Domain Adaptation Duke to MSMT DG-Net mAP 6.35 #11 of 13 Archive leaderboard report
Unsupervised Domain Adaptation Duke to MSMT DG-Net rank-1 20.59 #11 of 13 Archive leaderboard report
Unsupervised Domain Adaptation Duke to MSMT DG-Net rank-10 37.04 #11 of 13 Archive leaderboard report
Unsupervised Domain Adaptation Duke to MSMT DG-Net rank-5 31.67 #11 of 13 Archive leaderboard report
Unsupervised Domain Adaptation Duke to Market DG-Net mAP 26.83 #23 of 26 Archive leaderboard report
Unsupervised Domain Adaptation Duke to Market DG-Net rank-1 56.12 #23 of 26 Archive leaderboard report
Unsupervised Domain Adaptation Duke to Market DG-Net rank-10 78.12 #23 of 26 Archive leaderboard report
Unsupervised Domain Adaptation Duke to Market DG-Net rank-5 72.18 #23 of 26 Archive leaderboard report
Unsupervised Domain Adaptation Market to Duke DG-Net mAP 24.25 #22 of 25 Archive leaderboard report
Unsupervised Domain Adaptation Market to Duke DG-Net rank-1 42.62 #22 of 25 Archive leaderboard report
Unsupervised Domain Adaptation Market to Duke DG-Net rank-10 64.63 #22 of 25 Archive leaderboard report
Unsupervised Domain Adaptation Market to Duke DG-Net rank-5 58.57 #22 of 25 Archive leaderboard report
Unsupervised Domain Adaptation Market to MSMT DG-Net mAP 5.41 #15 of 17 Archive leaderboard report
Unsupervised Domain Adaptation Market to MSMT DG-Net rank-1 17.11 #15 of 17 Archive leaderboard report
Unsupervised Domain Adaptation Market to MSMT DG-Net rank-10 31.62 #15 of 17 Archive leaderboard report
Unsupervised Domain Adaptation Market to MSMT DG-Net rank-5 26.66 #15 of 17 Archive leaderboard report
Unsupervised Person Re-Identification DukeMTMC-reID->MSMT17 DGNet Rank-1 20.59 #6 of 7 Archive leaderboard report
Unsupervised Person Re-Identification DukeMTMC-reID->MSMT17 DGNet Rank-10 31.67 #6 of 7 Archive leaderboard report
Unsupervised Person Re-Identification DukeMTMC-reID->MSMT17 DGNet Rank-5 37.04 #6 of 7 Archive leaderboard report
Unsupervised Person Re-Identification DukeMTMC-reID->MSMT17 DGNet mAP 6.35 #6 of 7 Archive leaderboard report
Unsupervised Person Re-Identification DukeMTMC-reID->Market-1501 DGNet Rank-1 56.12 #6 of 8 Archive leaderboard report
Unsupervised Person Re-Identification DukeMTMC-reID->Market-1501 DGNet Rank-10 72.18 #6 of 8 Archive leaderboard report
Unsupervised Person Re-Identification DukeMTMC-reID->Market-1501 DGNet Rank-5 78.12 #6 of 8 Archive leaderboard report
Unsupervised Person Re-Identification DukeMTMC-reID->Market-1501 DGNet mAP 26.83 #6 of 8 Archive leaderboard report
Unsupervised Person Re-Identification MSMT17->DukeMTMC-reID DGNet Rank-1 61.89 #2 of 4 Archive leaderboard report
Unsupervised Person Re-Identification MSMT17->DukeMTMC-reID DGNet Rank-10 75.81 #2 of 4 Archive leaderboard report
Unsupervised Person Re-Identification MSMT17->DukeMTMC-reID DGNet Rank-5 80.34 #2 of 4 Archive leaderboard report
Unsupervised Person Re-Identification MSMT17->DukeMTMC-reID DGNet mAP 40.69 #2 of 4 Archive leaderboard report
Unsupervised Person Re-Identification MSMT17->Market-1501 DG-Net Rank-1 61.76 #2 of 3 Archive leaderboard report
Unsupervised Person Re-Identification MSMT17->Market-1501 DG-Net Rank-10 83.25 #2 of 3 Archive leaderboard report
Unsupervised Person Re-Identification MSMT17->Market-1501 DG-Net Rank-5 77.67 #2 of 3 Archive leaderboard report
Unsupervised Person Re-Identification MSMT17->Market-1501 DG-Net mAP 33.62 #2 of 3 Archive leaderboard report
Unsupervised Person Re-Identification Market-1501->DukeMTMC-reID DGNet Rank-1 42.62 #6 of 7 Archive leaderboard report
Unsupervised Person Re-Identification Market-1501->DukeMTMC-reID DGNet Rank-10 64.63 #6 of 7 Archive leaderboard report
Unsupervised Person Re-Identification Market-1501->DukeMTMC-reID DGNet Rank-5 58.57 #6 of 7 Archive leaderboard report
Unsupervised Person Re-Identification Market-1501->DukeMTMC-reID DGNet mAP 24.25 #6 of 7 Archive leaderboard report
Unsupervised Person Re-Identification Market-1501->MSMT17 DG-Net Rank-1 17.11 #6 of 7 Archive leaderboard report
Unsupervised Person Re-Identification Market-1501->MSMT17 DG-Net Rank-10 26.66 #6 of 7 Archive leaderboard report
Unsupervised Person Re-Identification Market-1501->MSMT17 DG-Net Rank-5 31.62 #6 of 7 Archive leaderboard report
Unsupervised Person Re-Identification Market-1501->MSMT17 DG-Net mAP 5.41 #6 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.

Methods

Introduced by this paper: DG-Net

DG-Net

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