Papers › Beyond Part Models: Person Retrieval with Refined Part Pooling (and a Strong...

Beyond Part Models: Person Retrieval with Refined Part Pooling (and a Strong Convolutional Baseline)

26 Nov 2017ECCV 2018 9arXiv:1711.09349archive 2025-07-28

Yifan Sun, Liang Zheng, Yi Yang, Qi Tian, Shengjin Wang

Employing part-level features for pedestrian image description offers fine-grained information and has been verified as beneficial for person retrieval in very recent literature. A prerequisite of part discovery is that each part should be well located. Instead of using external cues, e.g., pose estimation, to directly locate parts, this paper lays emphasis on the content consistency within each part. Specifically, we target at learning discriminative part-informed features for person retrieval and make two contributions. (i) A network named Part-based Convolutional Baseline (PCB). Given an image input, it outputs a convolutional descriptor consisting of several part-level features. With a uniform partition strategy, PCB achieves competitive results with the state-of-the-art methods, proving itself as a strong convolutional baseline for person retrieval. (ii) A refined part pooling (RPP) method. Uniform partition inevitably incurs outliers in each part, which are in fact more similar to other parts. RPP re-assigns these outliers to the parts they are closest to, resulting in refined parts with enhanced within-part consistency. Experiment confirms that RPP allows PCB to gain another round of performance boost. For instance, on the Market-1501 dataset, we achieve (77.4+4.2)% mAP and (92.3+1.5)% rank-1 accuracy, surpassing the state of the art by a large margin.

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

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

AndlollipopFU/PCB mentioned on GitHubpytorchSyntology: not harvested report
Calylyli/PCB_RPP mentioned on GitHubmindsporeSyntology: not harvested report
Demonhesusheng/Reid mentioned on GitHubpytorchMITSyntology: not harvested report
GuHongyang/Person-ReID-Pytorch mentioned on GitHubpytorchSyntology: not harvested report
HoganZhang/Person_reID_baseline_pytorch mentioned on GitHubpytorchSyntology: not harvested report
NIRVANALAN/reid_baseline mentioned on GitHubpytorchSyntology: not harvested report
Proxim123/person-reID-No1- mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Joint Discriminative and Generative Learning for Person Re-identification (arXiv:1904.07223; that paper's own run record: 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); nothing checks that they implement this paper's method. report
SurajDonthi/Clean-ST-ReID-Multi-Target-Multi-Camera-Tracking mentioned on GitHubpytorchSyntology: not harvested report
SurajDonthi/Multi-Camera-Person-Re-Identification mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Spatial-Temporal Person Re-identification (arXiv:1812.03282; that paper's own run record: 8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. report
SurajDonthi/Multi-Target-Multi-Camera-Tracking-ST-ReID mentioned on GitHubpytorchSyntology: not harvested report
SurajDonthi/Multi-Target-Multi-Camera-Tracking-ST-ReID-Clean-Code mentioned on GitHubpytorchSyntology: not harvested report
huanghoujing/beyond-part-models mentioned on GitHubpytorchSyntology: not harvested report
huanghoujing/person-reid-triplet-loss-baseline mentioned on GitHubpytorchSyntology: not harvested report
ivychill/reid mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Joint Discriminative and Generative Learning for Person Re-identification (arXiv:1904.07223; that paper's own run record: 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); nothing checks that they implement this paper's method. report
jiangsikai/Person_reID_baseline_pytorch mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Joint Discriminative and Generative Learning for Person Re-identification (arXiv:1904.07223; that paper's own run record: 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); nothing checks that they implement this paper's method. report
lsh110600/person_re_id mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Joint Discriminative and Generative Learning for Person Re-identification (arXiv:1904.07223; that paper's own run record: 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); nothing checks that they implement this paper's method. report
syfafterzy/PCB_RPP mentioned on GitHubpytorchSyntology: not harvested report
syfafterzy/pcb_rpp_for_reid mentioned on GitHubpytorchSyntology: not harvested report
taroogura/Person_reID_baseline_pytorch mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Joint Discriminative and Generative Learning for Person Re-identification (arXiv:1904.07223; that paper's own run record: 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); nothing checks that they implement this paper's method. report
wxb589/Person_reID_baseline_pytorch-master mentioned on GitHubpytorchMITSyntology: not harvested report
xuxu116/pytorch-reid-lite mentioned on GitHubpytorchSyntology: not harvested report
2023-MindSpore-1/ms-code-215 mindsporeSyntology: not harvested report
2023-MindSpore-1/ms-code-215 mindsporeSyntology: not harvested report
MS-Mind/MS-Code-06 mindsporeSyntology: not harvested report
Mind23-2/MindCode-5 mindsporeSyntology: not harvested report
Mind23-2/MindCode-5 mindsporeSyntology: not harvested report
MindSpore-paper-code-2/code2 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

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

Tasks

Person Re-IdentificationPerson RetrievalRetrieval

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Person Re-Identification DukeMTMC-reID PCB (RPP) Rank-1 83.3 #65 of 94 Archive leaderboard report
Person Re-Identification DukeMTMC-reID PCB (RPP) mAP 69.2 #65 of 94 Archive leaderboard report
Person Re-Identification DukeMTMC-reID PCB (UP) Rank-1 81.8 #70 of 94 Archive leaderboard report
Person Re-Identification DukeMTMC-reID PCB (UP) mAP 66.1 #70 of 94 Archive leaderboard report
Person Re-Identification Market-1501 PCB + RPP Rank-1 93.8 #82 of 135 Archive leaderboard report
Person Re-Identification Market-1501 PCB + RPP mAP 81.6 #82 of 135 Archive leaderboard report
Person Re-Identification Market-1501 PCB Rank-1 92.3 #89 of 135 Archive leaderboard report
Person Re-Identification Market-1501 PCB mAP 77.4 #89 of 135 Archive leaderboard report
Person Re-Identification Market-1501-C PCB Rank-1 34.93 #6 of 22 Archive leaderboard report
Person Re-Identification Market-1501-C PCB mAP 12.72 #6 of 22 Archive leaderboard report
Person Re-Identification Market-1501-C PCB mINP 0.41 #6 of 22 Archive leaderboard report
Person Re-Identification UAV-Human PCB Rank-1 62.19 #3 of 4 Archive leaderboard report
Person Re-Identification UAV-Human PCB Rank-5 83.90 #3 of 4 Archive leaderboard report
Person Re-Identification UAV-Human PCB mAP 61.05 #3 of 4 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: PCB

PCB

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