Papers › A Discriminatively Learned CNN Embedding for Person Re-identification

A Discriminatively Learned CNN Embedding for Person Re-identification

17 Nov 2016arXiv:1611.05666archive 2025-07-28

Zhedong Zheng, Liang Zheng, Yi Yang

We revisit two popular convolutional neural networks (CNN) in person re-identification (re-ID), i.e, verification and classification models. The two models have their respective advantages and limitations due to different loss functions. In this paper, we shed light on how to combine the two models to learn more discriminative pedestrian descriptors. Specifically, we propose a new siamese network that simultaneously computes identification loss and verification loss. Given a pair of training images, the network predicts the identities of the two images and whether they belong to the same identity. Our network learns a discriminative embedding and a similarity measurement at the same time, thus making full usage of the annotations. Albeit simple, the learned embedding improves the state-of-the-art performance on two public person re-ID benchmarks. Further, we show our architecture can also be applied in image retrieval.

PaperPDFCode

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

Code

layumi/2016_person_re-ID officialmentioned on GitHubpytorchMIT report
LDVC124/2016_person_re-ID mentioned on GitHubMIT report
layumi/Person-reID-verification 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

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

Tasks

General ClassificationImage RetrievalPerson Re-IdentificationRetrieval

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Retrieval Oxford5k Identification+Verification mAP 76.4 #2 of 2 Archive leaderboard report
Person Re-Identification CUHK03 DLCE MAP 86.4 #5 of 19 Archive leaderboard report
Person Re-Identification CUHK03 DLCE Rank-1 83.4 #5 of 19 Archive leaderboard report
Person Re-Identification DukeMTMC-reID DLCE Rank-1 68.9 #82 of 94 Archive leaderboard report
Person Re-Identification DukeMTMC-reID DLCE mAP 49.3 #82 of 94 Archive leaderboard report
Person Re-Identification MSMT17 DLCE Rank-1 60.48 #39 of 43 Archive leaderboard report
Person Re-Identification MSMT17 DLCE mAP 31.58 #39 of 43 Archive leaderboard report
Person Re-Identification Market-1501 DLCE Rank-1 79.51 #114 of 135 Archive leaderboard report
Person Re-Identification Market-1501 DLCE mAP 59.87 #114 of 135 Archive leaderboard report
Person Re-Identification Market-1501+500k DLCE MAP 45.24 #1 of 1 Archive leaderboard report
Person Re-Identification Market-1501+500k DLCE Rank-1 68.26 #1 of 1 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

Siamese Network

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