Tasks SotA Datasets Papers Methods Submit About

Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable Benchmarks All SotA Datasets Papers Methods

Community

Submit Results About

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Models/SOLIDER

SOLIDER

Reported on 14 benchmarks across 5 tasks · 1 paper · 1 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Computer Vision11 results

Person SearchonPRW
mAP· 2023-03-30
59.8
best: 61.2 (SPNet)
SOTA
Beyond Appearance: a Semantic Controllable Self-Supervised Learning Framework for Human-Centric Visual Tasks arXiv:2303.17602
Person SearchonCUHK-SYSU
MAP· 2023-03-30
95.5
best: 96.4 (SeqNeXt+GFN)
Beyond Appearance: a Semantic Controllable Self-Supervised Learning Framework for Human-Centric Visual Tasks arXiv:2303.17602
Person SearchonCUHK-SYSU
Top-1· 2023-03-30
95.8
best: 97 (SeqNeXt+GFN)
Beyond Appearance: a Semantic Controllable Self-Supervised Learning Framework for Human-Centric Visual Tasks arXiv:2303.17602
Person SearchonPRW
Top-1· 2023-03-30
86.7
best: 90.9 (SPNet)
Beyond Appearance: a Semantic Controllable Self-Supervised Learning Framework for Human-Centric Visual Tasks arXiv:2303.17602
Person Re-IdentificationonMarket-1501
Rank-1· 2023-03-30
96.9
best: 98 (st-ReID(RE, RK))
Beyond Appearance: a Semantic Controllable Self-Supervised Learning Framework for Human-Centric Visual Tasks arXiv:2303.17602
Person Re-IdentificationonMarket-1501
mAP· 2023-03-30
93.9
best: 96.21 (Unsupervised Pre-training (ResNet101+RK))
Beyond Appearance: a Semantic Controllable Self-Supervised Learning Framework for Human-Centric Visual Tasks arXiv:2303.17602
Person Re-IdentificationonOccluded-DukeMTMC
Rank-1· 2023-03-30
71.2
best: 84.31 (KPR + SOLIDER)
Beyond Appearance: a Semantic Controllable Self-Supervised Learning Framework for Human-Centric Visual Tasks arXiv:2303.17602
Person Re-IdentificationonOccluded-DukeMTMC
mAP· 2023-03-30
61.9
best: 75.11 (KPR + SOLIDER)
Beyond Appearance: a Semantic Controllable Self-Supervised Learning Framework for Human-Centric Visual Tasks arXiv:2303.17602
Pedestrian Attribute RecognitiononPA-100K
Accuracy· uses extra data· 2023-03-30
86.38
best: 90.8 (PATH (Partial FT))
Beyond Appearance: a Semantic Controllable Self-Supervised Learning Framework for Human-Centric Visual Tasks arXiv:2303.17602
Pedestrian DetectiononCityPersons
Heavy MR^-2· uses extra data· 2023-03-30
39.4
best: 56.9 (RepLoss)
Beyond Appearance: a Semantic Controllable Self-Supervised Learning Framework for Human-Centric Visual Tasks arXiv:2303.17602
Pedestrian DetectiononCityPersons
Reasonable MR^-2· uses extra data· 2023-03-30
9.7
best: 15.5 (TLL)
Beyond Appearance: a Semantic Controllable Self-Supervised Learning Framework for Human-Centric Visual Tasks arXiv:2303.17602

Robots3 results

Autonomous VehiclesonCityPersons
Heavy MR^-2· uses extra data· 2023-03-30
39.4
best: 56.9 (RepLoss)
Beyond Appearance: a Semantic Controllable Self-Supervised Learning Framework for Human-Centric Visual Tasks arXiv:2303.17602
Autonomous VehiclesonCityPersons
Reasonable MR^-2· uses extra data· 2023-03-30
9.7
best: 15.5 (TLL)
Beyond Appearance: a Semantic Controllable Self-Supervised Learning Framework for Human-Centric Visual Tasks arXiv:2303.17602
Autonomous VehiclesonPA-100K
Accuracy· uses extra data· 2023-03-30
86.38
best: 90.8 (PATH (Partial FT))
Beyond Appearance: a Semantic Controllable Self-Supervised Learning Framework for Human-Centric Visual Tasks arXiv:2303.17602