Papers › Beyond Appearance: a Semantic Controllable Self-Supervised Learning Framework for...

Beyond Appearance: a Semantic Controllable Self-Supervised Learning Framework for Human-Centric Visual Tasks

30 Mar 2023CVPR 2023 1arXiv:2303.17602archive 2025-07-28

Weihua Chen, Xianzhe Xu, Jian Jia, Hao Luo, Yaohua Wang, Fan Wang, Rong Jin, Xiuyu Sun

Human-centric visual tasks have attracted increasing research attention due to their widespread applications. In this paper, we aim to learn a general human representation from massive unlabeled human images which can benefit downstream human-centric tasks to the maximum extent. We call this method SOLIDER, a Semantic cOntrollable seLf-supervIseD lEaRning framework. Unlike the existing self-supervised learning methods, prior knowledge from human images is utilized in SOLIDER to build pseudo semantic labels and import more semantic information into the learned representation. Meanwhile, we note that different downstream tasks always require different ratios of semantic information and appearance information. For example, human parsing requires more semantic information, while person re-identification needs more appearance information for identification purpose. So a single learned representation cannot fit for all requirements. To solve this problem, SOLIDER introduces a conditional network with a semantic controller. After the model is trained, users can send values to the controller to produce representations with different ratios of semantic information, which can fit different needs of downstream tasks. Finally, SOLIDER is verified on six downstream human-centric visual tasks. It outperforms state of the arts and builds new baselines for these tasks. The code is released in https://github.com/tinyvision/SOLIDER.

PaperPDFConference PDFCodeCode 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="2303.17602")

Code

Syntology Ran 1 of 2 code samples harvested from 2 repositories linked to this paper; 1 has no recorded run. Of those that ran: 1 ran with no contract checked.

By repository: official repository: 1 sample from 1 repository, 0 ran; community (archive-listed): 1 sample from 1 repository, 1 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

tinyvision/SOLIDER officialmentioned in papermentioned on GitHubpytorch report
DengpanFu/LUPerson mentioned on GitHubpytorch report
hasanirtiza/Pedestron mentioned on GitHubpytorchApache-2.0 report
modelscope/modelscope pytorchApache-2.0 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

2 samples harvested; 1 ran; 0 honoured the contract we drafted; 1 has 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
1unverified

Licence: 1 of the 2 samples is 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. “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.

DINOLoss tinyvision/SOLIDER/main_solider.py official repository unverified Apache-2.0 (permissive) · e3eca5e066e1e795 · report
LUPNet DengpanFu/LUPerson/lup_moco/libs/encoder.py community (archive-listed) ran fingerprinted no licence file found · pointer only · d94422fb61f76b24 · report

Tasks

Human ParsingPedestrian Attribute RecognitionPedestrian DetectionPerson Re-IdentificationPerson SearchPose EstimationSelf-Supervised LearningSemantic Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Pedestrian Attribute Recognition PA-100K SOLIDER Accuracy 86.38 #5 of 13 Archive leaderboard report
Pedestrian Detection CityPersons SOLIDER Heavy MR^-2 39.4 #9 of 22 Archive leaderboard report
Pedestrian Detection CityPersons SOLIDER Reasonable MR^-2 9.7 #9 of 22 Archive leaderboard report
Person Re-Identification MSMT17 SOLIDER (with re-ranking) Rank-1 91.7 #2 of 43 Archive leaderboard report
Person Re-Identification MSMT17 SOLIDER (with re-ranking) mAP 86.5 #2 of 43 Archive leaderboard report
Person Re-Identification MSMT17 SOLIDER (without re-ranking) Rank-1 90.7 #6 of 43 Archive leaderboard report
Person Re-Identification MSMT17 SOLIDER (without re-ranking) mAP 77.1 #6 of 43 Archive leaderboard report
Person Re-Identification Market-1501 SOLIDER Rank-1 96.9 #7 of 135 Archive leaderboard report
Person Re-Identification Market-1501 SOLIDER mAP 93.9 #7 of 135 Archive leaderboard report
Person Re-Identification Market-1501 SOLIDER (RK) Rank-1 96.7 #10 of 135 Archive leaderboard report
Person Re-Identification Market-1501 SOLIDER (RK) mAP 95.6 #10 of 135 Archive leaderboard report
Person Re-Identification Occluded-DukeMTMC SOLIDER Rank-1 71.2 #7 of 32 Archive leaderboard report
Person Re-Identification Occluded-DukeMTMC SOLIDER mAP 61.9 #7 of 32 Archive leaderboard report
Person Search CUHK-SYSU SOLIDER MAP 95.5 #6 of 16 Archive leaderboard report
Person Search CUHK-SYSU SOLIDER Top-1 95.8 #6 of 16 Archive leaderboard report
Person Search PRW SOLIDER Top-1 86.7 #2 of 15 Archive leaderboard report
Person Search PRW SOLIDER mAP 59.8 #2 of 15 Archive leaderboard report
Pose Estimation COCO (Common Objects in Context) SOLIDER (swin-B) AP 76.6 #8 of 10 Archive leaderboard report
Pose Estimation COCO (Common Objects in Context) SOLIDER (swin-B) AR 81.5 #8 of 10 Archive leaderboard report
Semantic Segmentation LIP val SOLIDER mIoU 60.50% #4 of 13 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