Papers › Unlabeled Samples Generated by GAN Improve the Person Re-identification Baseline in vitro

Unlabeled Samples Generated by GAN Improve the Person Re-identification Baseline in vitro

26 Jan 2017ICCV 2017 10arXiv:1701.07717archive 2025-07-28

Zhedong Zheng, Liang Zheng, Yi Yang

The main contribution of this paper is a simple semi-supervised pipeline that only uses the original training set without collecting extra data. It is challenging in 1) how to obtain more training data only from the training set and 2) how to use the newly generated data. In this work, the generative adversarial network (GAN) is used to generate unlabeled samples. We propose the label smoothing regularization for outliers (LSRO). This method assigns a uniform label distribution to the unlabeled images, which regularizes the supervised model and improves the baseline. We verify the proposed method on a practical problem: person re-identification (re-ID). This task aims to retrieve a query person from other cameras. We adopt the deep convolutional generative adversarial network (DCGAN) for sample generation, and a baseline convolutional neural network (CNN) for representation learning. Experiments show that adding the GAN-generated data effectively improves the discriminative ability of learned CNN embeddings. On three large-scale datasets, Market-1501, CUHK03 and DukeMTMC-reID, we obtain +4.37%, +1.6% and +2.46% improvement in rank-1 precision over the baseline CNN, respectively. We additionally apply the proposed method to fine-grained bird recognition and achieve a +0.6% improvement over a strong baseline. The code is available at https://github.com/layumi/Person-reID_GAN.

PaperPDFConference PDFCode

In Syntology View this paper on Syntology, its page in Syntology's graph. That page 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

layumi/Person-reID_GAN officialmentioned in papermentioned on GitHubtfMITSyntology: not harvested report
AI-NERC-NUPT/DDB mentioned on GitHubpytorchSyntology: not harvested report
AI-NERC-NUPT/PFH-OSNet mentioned on GitHubpytorchSyntology: not harvested report
AI-NERC-NUPT/PLR-OSNet mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Learning Diverse Features with Part-Level Resolution for Person Re-Identification (arXiv:2001.07442; that paper's own run record: 0 ran · 1 unverified); nothing checks that they implement this paper's method. report
freeSubmission/SDB mentioned on GitHubpytorchSyntology: not harvested report
hbchen121/dgreid mentioned on GitHubpytorchSyntology: not harvested report
lyy973/OSFA mentioned on GitHubpytorchSyntology: not harvested report
whj363636/Adversarial-attack-on-Person-ReID-With-Deep-Mis-Ranking mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Transferable, Controllable, and Inconspicuous Adversarial Attacks on Person... (arXiv:2004.04199; that paper's own run record: 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. 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

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

Tasks

Fine-Grained Image ClassificationPerson Re-IdentificationRepresentation Learning

1 archive task tag without a task page not shown.

Datasets

Introduced by this paper, per the archive.

DukeMTMC-attribute

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Fine-Grained Image Classification CUB-200-2011 Basel.+LSRO Accuracy 84.4 #28 of 30 Archive leaderboard report
Person Re-Identification CUHK03 VI+LSRO 3 MAP 87.4 #4 of 19 Archive leaderboard report
Person Re-Identification CUHK03 VI+LSRO 3 Rank-1 84.6 #4 of 19 Archive leaderboard report
Person Re-Identification DukeMTMC-reID GAN Rank-1 67.68 #86 of 94 Archive leaderboard report
Person Re-Identification DukeMTMC-reID GAN mAP 47.13 #86 of 94 Archive leaderboard report
Person Re-Identification Market-1501 GAN Rank-1 83.97 #108 of 135 Archive leaderboard report
Person Re-Identification Market-1501 GAN mAP 66.07 #108 of 135 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