Papers › Learning Generalisable Omni-Scale Representations for Person Re-Identification

Learning Generalisable Omni-Scale Representations for Person Re-Identification

15 Oct 2019arXiv:1910.06827archive 2025-07-28

Kaiyang Zhou, Yongxin Yang, Andrea Cavallaro, Tao Xiang

An effective person re-identification (re-ID) model should learn feature representations that are both discriminative, for distinguishing similar-looking people, and generalisable, for deployment across datasets without any adaptation. In this paper, we develop novel CNN architectures to address both challenges. First, we present a re-ID CNN termed omni-scale network (OSNet) to learn features that not only capture different spatial scales but also encapsulate a synergistic combination of multiple scales, namely omni-scale features. The basic building block consists of multiple convolutional streams, each detecting features at a certain scale. For omni-scale feature learning, a unified aggregation gate is introduced to dynamically fuse multi-scale features with channel-wise weights. OSNet is lightweight as its building blocks comprise factorised convolutions. Second, to improve generalisable feature learning, we introduce instance normalisation (IN) layers into OSNet to cope with cross-dataset discrepancies. Further, to determine the optimal placements of these IN layers in the architecture, we formulate an efficient differentiable architecture search algorithm. Extensive experiments show that, in the conventional same-dataset setting, OSNet achieves state-of-the-art performance, despite being much smaller than existing re-ID models. In the more challenging yet practical cross-dataset setting, OSNet beats most recent unsupervised domain adaptation methods without using any target data. Our code and models are released at \texttt{https://github.com/KaiyangZhou/deep-person-reid}.

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="1910.06827")

Code

Syntology Ran 6 of 9 code samples harvested from 2 repositories linked to this paper; 3 have no recorded run. Of those that ran: 1 ran · honoured contract; 4 ran · our draft was wrong; 1 ran · fixture could not drive it.

By repository: community (archive-listed): 6 samples from 2 repositories, 5 ran; 3 identical to code first harvested elsewhere. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

KaiyangZhou/deep-person-reid officialmentioned in papermentioned on GitHubpytorchMIT report
LeDuySon/torchreid_uet_lab mentioned on GitHubpytorchMIT report
MatthewAbugeja/osnet mentioned on GitHubpytorch report
hukefei/deep-person-reid-master mentioned on GitHubpytorchMIT report
jacobtyo/mudd mentioned on GitHubpytorch report
openvinotoolkit/deep-object-reid mentioned on GitHubpytorchNOASSERTION report
tomektarabasz/deep_person_reid mentioned on GitHubpytorch report
mszpc/osnet mindspore 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

9 samples harvested; 6 ran; 1 honoured the contract we drafted; 3 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
4ran · our draft was wrong
1ran · fixture could not drive it
3unverified

Licence: 6 of the 9 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. Some samples are identical code Syntology first harvested from another repository; for those, this paper's copy is not located and its licence is not recorded. “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.

file_size jacobtyo/mudd/tools/export.py community (archive-listed) ran · honoured contract fingerprinted no licence file found · pointer only · a912fc7b24219286 · report
get_model_name jacobtyo/mudd/tools/export.py community (archive-listed) ran · our draft was wrong fingerprinted no licence file found · pointer only · c5cdc64a6b2b4eee · report
merge mszpc/osnet/osnet/model_utils/config.py community (archive-listed) ran · our draft was wrong Apache-2.0 (permissive) · b9e24c3e3e0e88a7 · report
parse_cli_to_yaml mszpc/osnet/osnet/model_utils/config.py community (archive-listed) ran · our draft was wrong Apache-2.0 (permissive) · ff75f4d130ead571 · report
parse_yaml mszpc/osnet/osnet/model_utils/config.py community (archive-listed) ran · our draft was wrong Apache-2.0 (permissive) · 8486896224aa5191 · report
export_onnx jacobtyo/mudd/tools/export.py community (archive-listed) unverified no licence file found · pointer only · bae3b33459f2e29c · report
osnet_x1_0 identical code first harvested elsewhere ran · fixture could not drive it licence of this copy not recorded · 326803f4dfec5af1 · report
init_pretrained_weights identical code first harvested elsewhere unverified licence of this copy not recorded · bd41824b39412f93 · report
osnet_x0_75 identical code first harvested elsewhere unverified licence of this copy not recorded · 33a8877d1eb68984 · report

Tasks

Domain AdaptationPerson Re-IdentificationUnsupervised Domain AdaptationUnsupervised Person Re-Identification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Unsupervised Person Re-Identification DukeMTMC-reID->Market-1501 OSNet-AIN Rank-1 61 #5 of 8 Archive leaderboard report
Unsupervised Person Re-Identification DukeMTMC-reID->Market-1501 OSNet-AIN Rank-10 82.5 #5 of 8 Archive leaderboard report
Unsupervised Person Re-Identification DukeMTMC-reID->Market-1501 OSNet-AIN Rank-5 77 #5 of 8 Archive leaderboard report
Unsupervised Person Re-Identification DukeMTMC-reID->Market-1501 OSNet-AIN mAP 30.6 #5 of 8 Archive leaderboard report
Unsupervised Person Re-Identification MSMT17->DukeMTMC-reID OSNet-AIN Rank-1 70.1 #1 of 4 Archive leaderboard report
Unsupervised Person Re-Identification MSMT17->DukeMTMC-reID OSNet-AIN Rank-10 88.6 #1 of 4 Archive leaderboard report
Unsupervised Person Re-Identification MSMT17->DukeMTMC-reID OSNet-AIN Rank-5 84.1 #1 of 4 Archive leaderboard report
Unsupervised Person Re-Identification MSMT17->DukeMTMC-reID OSNet-AIN mAP 43.3 #1 of 4 Archive leaderboard report
Unsupervised Person Re-Identification MSMT17->Market-1501 OSNet-AIN Rank-1 71.1 #1 of 3 Archive leaderboard report
Unsupervised Person Re-Identification MSMT17->Market-1501 OSNet-AIN Rank-10 86.4 #1 of 3 Archive leaderboard report
Unsupervised Person Re-Identification MSMT17->Market-1501 OSNet-AIN Rank-5 83.3 #1 of 3 Archive leaderboard report
Unsupervised Person Re-Identification MSMT17->Market-1501 OSNet-AIN mAP 52.7 #1 of 3 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