Papers › Omni-Scale Feature Learning for Person Re-Identification

Omni-Scale Feature Learning for Person Re-Identification

2 May 2019ICCV 2019 10arXiv:1905.00953archive 2025-07-28

Kaiyang Zhou, Yongxin Yang, Andrea Cavallaro, Tao Xiang

As an instance-level recognition problem, person re-identification (ReID) relies on discriminative features, which not only capture different spatial scales but also encapsulate an arbitrary combination of multiple scales. We call features of both homogeneous and heterogeneous scales omni-scale features. In this paper, a novel deep ReID CNN is designed, termed Omni-Scale Network (OSNet), for omni-scale feature learning. This is achieved by designing a residual block composed of multiple convolutional streams, each detecting features at a certain scale. Importantly, a novel unified aggregation gate is introduced to dynamically fuse multi-scale features with input-dependent channel-wise weights. To efficiently learn spatial-channel correlations and avoid overfitting, the building block uses pointwise and depthwise convolutions. By stacking such block layer-by-layer, our OSNet is extremely lightweight and can be trained from scratch on existing ReID benchmarks. Despite its small model size, OSNet achieves state-of-the-art performance on six person ReID datasets, outperforming most large-sized models, often by a clear margin. Code and models are available at: https://github.com/KaiyangZhou/deep-person-reid.

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

No sample from the archive's official repository (KaiyangZhou/deep-person-reid) is linked to this paper; the 26 samples below come from 4 community repositories. Syntology harvested code from KaiyangZhou/deep-person-reid for another paper.

KaiyangZhou/deep-person-reid: Syntology's graph links these samples to Torchreid: A Library for Deep Learning Person Re-Identification in Pytorch (arXiv:1910.10093; that paper's own run record: 11 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 1 where Syntology's instrument failed) · 13 unverified); nothing checks that they implement this paper's method.

Syntology 26 code samples harvested from 4 repositories linked to this paper: 14 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 2 where Syntology's instrument failed) · 12 unverified. Where Syntology's instrument failed: 2 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 26 samples from 4 repositories, 14 ran (12 with no instrument failure; 2 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 3 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.

17 repositories listed; official and paper-mentioned ones first.

KaiyangZhou/deep-person-reid officialmentioned in papermentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Torchreid: A Library for Deep Learning Person Re-Identification in Pytorch (arXiv:1910.10093; that paper's own run record: 11 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 1 where Syntology's instrument failed) · 13 unverified); nothing checks that they implement this paper's method. report
InnovArul/vidreid_cosegmentation mentioned on GitHubpytorchApache-2.0Syntology: 8 samples, 5 ran (0 instrument-failed) · 3 unverified report
LeDuySon/torchreid_uet_lab mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Torchreid: A Library for Deep Learning Person Re-Identification in Pytorch (arXiv:1910.10093; that paper's own run record: 11 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 1 where Syntology's instrument failed) · 13 unverified); nothing checks that they implement this paper's method. report
MatthewAbugeja/osnet mentioned on GitHubpytorchSyntology: 3 samples, 1 ran (1 instrument-failed) · 2 unverified report
RodMech/OSNet-IBN1-Lite mentioned on GitHubpytorchSyntology: not harvested report
Yanghojun/Custom_yolov5_pytorch mentioned on GitHubpytorchGPL-3.0Syntology: not harvested report
donnjonn/Masterproef mentioned on GitHubpytorchMITSyntology: 13 samples, 7 ran (0 instrument-failed) · 6 unverified report
hukefei/deep-person-reid-master mentioned on GitHubpytorchMITSyntology: not harvested report
jacobtyo/mudd mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Learning Generalisable Omni-Scale Representations for Person Re-Identification (arXiv:1910.06827; that paper's own run record: 6 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 5 where Syntology's instrument failed) · 3 unverified); nothing checks that they implement this paper's method. report
mikel-brostrom/boxmot mentioned on GitHubpytorchAGPL-3.0Syntology: not harvested report
mikel-brostrom/yolov7_strongsort_osnet mentioned on GitHubpytorchGPL-3.0Syntology: not harvested report
openvinotoolkit/deep-object-reid mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
tomektarabasz/deep_person_reid mentioned on GitHubpytorchSyntology: 2 samples, 1 ran (1 instrument-failed) · 1 unverified report
2023-MindSpore-1/ms-code-215 mindsporeSyntology: not harvested report
Mind23-2/MindCode-101 mindsporeSyntology: not harvested report
MindSpore-paper-code-2/code2 mindsporeSyntology: not harvested report
code-implementation1/Code6 mindsporeSyntology: 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

26 samples harvested: 14 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 2 where Syntology's instrument failed) · 12 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; the contract check could not run
12ran
12unverified

Licence: 3 of the 26 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 4 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.

InnovArul/vidreid_cosegmentation community (archive-listed) 8 samples, 5 ran (0 instrument-failed) · 3 unverified
evaluate in 514 papers src/eval_metrics.py ran fingerprinted Apache-2.0 (permissive) · 2267200bffdf674d · 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 2026-09-25
get_gaussian_kernel in 17 papers src/utils.py ran Apache-2.0 (permissive) · 5691966090d9a9f2 · report fixture: signature channels:int/0/int, kernel_size:int/0/int, mean:int/0/int, sigma:list/1/int · returned Tensor · level recorded 2026-09-24
load_pretrained_model in 40 papers src/utils.py ran Apache-2.0 (permissive) · b2e664243298ae49 · report fixture: signature model:callable/0/?, pretrained_model_path:str/0/str, verbose:bool/0/bool · returned SimpleModel · level recorded 2026-09-24
read_image in 73 papers src/video_loader.py ran Apache-2.0 (permissive) · 80bda819706e052f · report fixture: signature img_path:str/0/str · returned Image · level recorded 2026-09-25
set_stride src/utils.py ran Apache-2.0 (permissive) · ace193c5fdd754c7 · report fixture: signature module:callable/0/?, stride:int/0/int · returned MaxPool2d · level recorded 2026-09-24
get_ResNet src/models/ResNet.py unverified Apache-2.0 (permissive) · a3648945de135b45 · report
read_Duke_attributes src/project_utils.py unverified Apache-2.0 (permissive) · 7b9d4d5659f1503e · report
shortlist_Duke_on_attribute src/project_utils.py unverified Apache-2.0 (permissive) · 3c98b3b1ea1f4111 · report
MatthewAbugeja/osnet community (archive-listed) 3 samples, 1 ran (1 instrument-failed) · 2 unverified
osnet_x1_0 in 5 papers torchreid/models/osnet.py ran; the contract check could not run (DEP_MISSING) · metamorphic tier: deterministic no licence file found · pointer only · 326803f4dfec5af1 · report fixture: signature num_classes:int/0/int, pretrained:bool/0/bool, model:callable/0/?, x:Tensor/4/float, y:Tensor/1/int, criterion:callable/0/?, optimizer:SGD/0/?, feature_dim:int/0/int · returned OSNet · level recorded 2026-09-22
init_pretrained_weights in 5 papers torchreid/models/osnet.py unverified no licence file found · pointer only · bd41824b39412f93 · report
osnet_x0_75 in 5 papers torchreid/models/osnet.py unverified no licence file found · pointer only · 33a8877d1eb68984 · report
donnjonn/Masterproef community (archive-listed) 13 samples, 7 ran (0 instrument-failed) · 6 unverified
imagedata_kwargs in 7 papers deprecated/default_parser.py ran MIT (permissive) · 743ef3f8a8442fdc · report fixture: signature parsed_args:MockArgs/0/? · returned dict · level recorded 2026-09-24
inceptionresnetv2 in 10 papers torchreid/models/inceptionresnetv2.py ran MIT (permissive) · 0c2afba5ccb6bcc2 · report fixture: signature num_classes:int/0/int, pretrained:bool/0/bool · returned InceptionResNetV2 · level recorded 2026-09-25
inceptionv4 in 8 papers torchreid/models/inceptionv4.py ran MIT (permissive) · 2bcd3828691ac1d1 · report fixture: signature num_classes:int/0/int, pretrained:bool/0/bool, in_channels:int/0/int · returned InceptionV4 · level recorded 2026-09-25
mlfn in 6 papers torchreid/models/mlfn.py ran MIT (permissive) · b52023dd659c7a90 · report fixture: signature num_classes:int/0/int, loss:str/0/str, groups:int/0/int, channels:list/1/int, embed_dim:int/0/int · returned MLFN · level recorded 2026-09-25
nasnetamobile torchreid/models/nasnet.py ran MIT (permissive) · 9635afee4069aa90 · report fixture: signature num_classes:int/0/int, pretrained:bool/0/bool, input_size:list/1/int · returned NASNetAMobile · level recorded 2026-09-24
optimizer_kwargs in 13 papers deprecated/default_parser.py ran MIT (permissive) · cd21e7c823505eec · report fixture: signature parsed_args:ParsedArgs/0/? · returned dict · level recorded 2026-09-24
videodata_kwargs in 7 papers deprecated/default_parser.py ran MIT (permissive) · 3ab53e45735427cd · report fixture: signature parsed_args:Namespace/0/? · returned dict · level recorded 2026-09-24
densenet121 in 43 papers torchreid/models/densenet.py unverified MIT (permissive) · 6473856732e614c2 · report
densenet169 in 42 papers torchreid/models/densenet.py unverified MIT (permissive) · e271cdd444e9c43d · report
densenet201 in 21 papers torchreid/models/densenet.py unverified MIT (permissive) · 14ea88b72b8a45f3 · report
inceptionresnetv2 in 10 papers torchreid/models/inceptionresnetv2.py unverified MIT (permissive) · 968ff7bf292adbec · report
mobilenetv2_x1_0 in 7 papers torchreid/models/mobilenetv2.py unverified MIT (permissive) · 85b4bac4b8d2c9e4 · report
mobilenetv2_x1_4 in 7 papers torchreid/models/mobilenetv2.py unverified MIT (permissive) · 92bf5ac4db6e8f28 · report
tomektarabasz/deep_person_reid community (archive-listed) 2 samples, 1 ran (1 instrument-failed) · 1 unverified
osnet_x1_0 in 5 papers torchreid/models/osnet.py ran; the contract check could not run (DEP_MISSING) · metamorphic tier: deterministic MIT (permissive) · fdccc5451defed44 · report fixture: signature num_classes:int/0/int, pretrained:bool/0/bool, loss:str/0/str · returned OSNet · level recorded 2026-09-22
osnet_x0_75 in 5 papers torchreid/models/osnet.py unverified MIT (permissive) · 16bd38cf739b99e5 · report

Tasks

Person Re-Identification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Person Re-Identification CUHK03 OSNet MAP 67.8 #11 of 19 Archive leaderboard report
Person Re-Identification CUHK03 detected OSNet (ICCV'19) MAP 67.8 #10 of 19 Archive leaderboard report
Person Re-Identification CUHK03 detected OSNet (ICCV'19) Rank-1 72.3 #10 of 19 Archive leaderboard report
Person Re-Identification DukeMTMC-reID OSNet (ICCV'19) Rank-1 88.6 #61 of 94 Archive leaderboard report
Person Re-Identification DukeMTMC-reID OSNet (ICCV'19) mAP 73.5 #61 of 94 Archive leaderboard report
Person Re-Identification MSMT17 OSNet Rank-1 78.7 #33 of 43 Archive leaderboard report
Person Re-Identification MSMT17 OSNet mAP 52.9 #33 of 43 Archive leaderboard report
Person Re-Identification MSMT17-C OS-Net Rank-1 28.51 #2 of 5 Archive leaderboard report
Person Re-Identification MSMT17-C OS-Net mAP 7.86 #2 of 5 Archive leaderboard report
Person Re-Identification MSMT17-C OS-Net mINP 0.08 #2 of 5 Archive leaderboard report
Person Re-Identification Market-1501 OSNet Rank-1 94.8 #74 of 135 Archive leaderboard report
Person Re-Identification Market-1501 OSNet mAP 84.9 #74 of 135 Archive leaderboard report
Person Re-Identification Market-1501-C OS-Net Rank-1 30.94 #14 of 22 Archive leaderboard report
Person Re-Identification Market-1501-C OS-Net mAP 10.37 #14 of 22 Archive leaderboard report
Person Re-Identification Market-1501-C OS-Net mINP 0.23 #14 of 22 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

Batch NormalizationConvolutionReLUResidual BlockResidual Connection

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