TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

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

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

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

Models/CenterNet (HRNetV2-W48)

CenterNet (HRNetV2-W48)

Reported on 20 benchmarks across 5 tasks · 1 paper

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

Methodology16 results

  • 3DonCOCO test-dev
    AP75· 2019-08-20
    46.5
    best: 88.2 (ViTPose (ViTAE-G, ensemble))
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • 3DonCOCO test-dev
    APL· 2019-08-20
    57.8
    best: 86.5 (PoseBH-H)
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • 3DonCOCO test-dev
    APS· 2019-08-20
    22.2
    best: 48.6 (Focal-Stable-DINO (Focal-Huge, no TTA))
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • 3DonCOCO test-dev
    box mAP· 2019-08-20
    43.5
    best: 66 (Co-DETR)
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • 2D ClassificationonCOCO test-dev
    AP75· 2019-08-20
    46.5
    best: 71.7 (EVA)
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • 2D ClassificationonCOCO test-dev
    APL· 2019-08-20
    57.8
    best: 78 (Focal-Stable-DINO (Focal-Huge, no TTA))
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • 2D ClassificationonCOCO test-dev
    APS· 2019-08-20
    22.2
    best: 48.6 (Focal-Stable-DINO (Focal-Huge, no TTA))
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • 2D ClassificationonCOCO test-dev
    box mAP· 2019-08-20
    43.5
    best: 66 (Co-DETR)
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • 2D Object DetectiononCOCO test-dev
    AP75· 2019-08-20
    46.5
    best: 71.7 (EVA)
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • 2D Object DetectiononCOCO test-dev
    APL· 2019-08-20
    57.8
    best: 78 (Focal-Stable-DINO (Focal-Huge, no TTA))
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • 2D Object DetectiononCOCO test-dev
    APS· 2019-08-20
    22.2
    best: 48.6 (Focal-Stable-DINO (Focal-Huge, no TTA))
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • 2D Object DetectiononCOCO test-dev
    box mAP· 2019-08-20
    43.5
    best: 66 (Co-DETR)
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • 16konCOCO test-dev
    AP75· 2019-08-20
    46.5
    best: 71.7 (EVA)
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • 16konCOCO test-dev
    APL· 2019-08-20
    57.8
    best: 78 (Focal-Stable-DINO (Focal-Huge, no TTA))
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • 16konCOCO test-dev
    APS· 2019-08-20
    22.2
    best: 48.6 (Focal-Stable-DINO (Focal-Huge, no TTA))
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • 16konCOCO test-dev
    box mAP· 2019-08-20
    43.5
    best: 66 (Co-DETR)
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919

Computer Vision4 results

  • Object DetectiononCOCO test-dev
    AP75· 2019-08-20
    46.5
    best: 71.7 (EVA)
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • Object DetectiononCOCO test-dev
    APL· 2019-08-20
    57.8
    best: 78 (Focal-Stable-DINO (Focal-Huge, no TTA))
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • Object DetectiononCOCO test-dev
    APS· 2019-08-20
    22.2
    best: 48.6 (Focal-Stable-DINO (Focal-Huge, no TTA))
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919
  • Object DetectiononCOCO test-dev
    box mAP· 2019-08-20
    43.5
    best: 66 (Co-DETR)
    Deep High-Resolution Representation Learning for Visual RecognitionarXiv:1908.07919