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/GLIP (Swin-L, multi-scale)

GLIP (Swin-L, multi-scale)

Reported on 35 benchmarks across 5 tasks · 1 paper · 21 SOTA

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

Methodology28 results

  • 3DonCOCO test-dev
    APS· 2021-12-07
    45.3
    best: 48.6 (Focal-Stable-DINO (Focal-Huge, no TTA))
    SOTA
    Grounded Language-Image Pre-trainingarXiv:2112.03857
  • 2D ClassificationonCOCO test-dev
    AP50· 2021-12-07
    79.5
    best: 82.1 (Plain-DETR (Swin-L))
    SOTA
    Grounded Language-Image Pre-trainingarXiv:2112.03857
  • 2D ClassificationonCOCO test-dev
    AP75· 2021-12-07
    67.7
    best: 71.7 (EVA)
    SOTA
    Grounded Language-Image Pre-trainingarXiv:2112.03857
  • 2D ClassificationonCOCO test-dev
    APL· 2021-12-07
    75
    best: 78 (Focal-Stable-DINO (Focal-Huge, no TTA))
    SOTA
    Grounded Language-Image Pre-trainingarXiv:2112.03857
  • 2D ClassificationonCOCO test-dev
    APM· 2021-12-07
    64.9
    best: 67.7 (EVA)
    SOTA
    Grounded Language-Image Pre-trainingarXiv:2112.03857
  • 2D ClassificationonCOCO test-dev
    APS· 2021-12-07
    45.3
    best: 48.6 (Focal-Stable-DINO (Focal-Huge, no TTA))
    SOTA
    Grounded Language-Image Pre-trainingarXiv:2112.03857
  • 2D Object DetectiononCOCO test-dev
    AP50· 2021-12-07
    79.5
    best: 82.1 (Plain-DETR (Swin-L))
    SOTA
    Grounded Language-Image Pre-trainingarXiv:2112.03857
  • 2D Object DetectiononCOCO test-dev
    AP75· 2021-12-07
    67.7
    best: 71.7 (EVA)
    SOTA
    Grounded Language-Image Pre-trainingarXiv:2112.03857
  • 2D Object DetectiononCOCO test-dev
    APL· 2021-12-07
    75
    best: 78 (Focal-Stable-DINO (Focal-Huge, no TTA))
    SOTA
    Grounded Language-Image Pre-trainingarXiv:2112.03857
  • 2D Object DetectiononCOCO test-dev
    APM· 2021-12-07
    64.9
    best: 67.7 (EVA)
    SOTA
    Grounded Language-Image Pre-trainingarXiv:2112.03857
  • 2D Object DetectiononCOCO test-dev
    APS· 2021-12-07
    45.3
    best: 48.6 (Focal-Stable-DINO (Focal-Huge, no TTA))
    SOTA
    Grounded Language-Image Pre-trainingarXiv:2112.03857
  • 16konCOCO test-dev
    AP50· 2021-12-07
    79.5
    best: 82.1 (Plain-DETR (Swin-L))
    SOTA
    Grounded Language-Image Pre-trainingarXiv:2112.03857
  • 16konCOCO test-dev
    AP75· 2021-12-07
    67.7
    best: 71.7 (EVA)
    SOTA
    Grounded Language-Image Pre-trainingarXiv:2112.03857
  • 16konCOCO test-dev
    APL· 2021-12-07
    75
    best: 78 (Focal-Stable-DINO (Focal-Huge, no TTA))
    SOTA
    Grounded Language-Image Pre-trainingarXiv:2112.03857
  • 16konCOCO test-dev
    APM· 2021-12-07
    64.9
    best: 67.7 (EVA)
    SOTA
    Grounded Language-Image Pre-trainingarXiv:2112.03857
  • 16konCOCO test-dev
    APS· 2021-12-07
    45.3
    best: 48.6 (Focal-Stable-DINO (Focal-Huge, no TTA))
    SOTA
    Grounded Language-Image Pre-trainingarXiv:2112.03857
  • 3DonCOCO test-dev
    AP50· 2021-12-07
    79.5
    best: 95 (ViTPose (ViTAE-G, ensemble))
    Grounded Language-Image Pre-trainingarXiv:2112.03857
  • 3DonCOCO test-dev
    AP75· 2021-12-07
    67.7
    best: 88.2 (ViTPose (ViTAE-G, ensemble))
    Grounded Language-Image Pre-trainingarXiv:2112.03857
  • 3DonCOCO test-dev
    APL· 2021-12-07
    75
    best: 86.5 (PoseBH-H)
    Grounded Language-Image Pre-trainingarXiv:2112.03857
  • 3DonCOCO test-dev
    APM· 2021-12-07
    64.9
    best: 83.8 (4xRSN-50 (ensemble))
    Grounded Language-Image Pre-trainingarXiv:2112.03857
  • 3DonCOCO test-dev
    box mAP· 2021-12-07
    61.5
    best: 66 (Co-DETR)
    Grounded Language-Image Pre-trainingarXiv:2112.03857
  • 3DonCOCO minival
    box AP· uses extra data· 2021-12-07
    60.8
    best: 66 (PE_spatial (DETA))
    Grounded Language-Image Pre-trainingarXiv:2112.03857
  • 2D ClassificationonCOCO test-dev
    box mAP· 2021-12-07
    61.5
    best: 66 (Co-DETR)
    Grounded Language-Image Pre-trainingarXiv:2112.03857
  • 2D ClassificationonCOCO minival
    box AP· uses extra data· 2021-12-07
    60.8
    best: 66 (PE_spatial (DETA))
    Grounded Language-Image Pre-trainingarXiv:2112.03857
  • 2D Object DetectiononCOCO test-dev
    box mAP· 2021-12-07
    61.5
    best: 66 (Co-DETR)
    Grounded Language-Image Pre-trainingarXiv:2112.03857
  • 2D Object DetectiononCOCO minival
    box AP· uses extra data· 2021-12-07
    60.8
    best: 66 (PE_spatial (DETA))
    Grounded Language-Image Pre-trainingarXiv:2112.03857
  • 16konCOCO test-dev
    box mAP· 2021-12-07
    61.5
    best: 66 (Co-DETR)
    Grounded Language-Image Pre-trainingarXiv:2112.03857
  • 16konCOCO minival
    box AP· uses extra data· 2021-12-07
    60.8
    best: 66 (PE_spatial (DETA))
    Grounded Language-Image Pre-trainingarXiv:2112.03857

Computer Vision7 results

  • Object DetectiononCOCO test-dev
    AP50· 2021-12-07
    79.5
    best: 82.1 (Plain-DETR (Swin-L))
    SOTA
    Grounded Language-Image Pre-trainingarXiv:2112.03857
  • Object DetectiononCOCO test-dev
    AP75· 2021-12-07
    67.7
    best: 71.7 (EVA)
    SOTA
    Grounded Language-Image Pre-trainingarXiv:2112.03857
  • Object DetectiononCOCO test-dev
    APL· 2021-12-07
    75
    best: 78 (Focal-Stable-DINO (Focal-Huge, no TTA))
    SOTA
    Grounded Language-Image Pre-trainingarXiv:2112.03857
  • Object DetectiononCOCO test-dev
    APM· 2021-12-07
    64.9
    best: 67.7 (EVA)
    SOTA
    Grounded Language-Image Pre-trainingarXiv:2112.03857
  • Object DetectiononCOCO test-dev
    APS· 2021-12-07
    45.3
    best: 48.6 (Focal-Stable-DINO (Focal-Huge, no TTA))
    SOTA
    Grounded Language-Image Pre-trainingarXiv:2112.03857
  • Object DetectiononCOCO test-dev
    box mAP· 2021-12-07
    61.5
    best: 66 (Co-DETR)
    Grounded Language-Image Pre-trainingarXiv:2112.03857
  • Object DetectiononCOCO minival
    box AP· uses extra data· 2021-12-07
    60.8
    best: 66 (PE_spatial (DETA))
    Grounded Language-Image Pre-trainingarXiv:2112.03857