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/DyHead (Swin-T, multi scale)

DyHead (Swin-T, multi scale)

Reported on 15 benchmarks across 5 tasks · 1 paper · 15 SOTA

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

Methodology12 results

  • 3DonCOCO 2017 val
    AP50· 2021-06-15
    68
    best: 79 (Mr. DETR (Swin-L, 1x, 5cale))
    SOTA
    Dynamic Head: Unifying Object Detection Heads with AttentionsarXiv:2106.08322
  • 3DonCOCO 2017 val
    AP75· 2021-06-15
    54.3
    best: 67.6 (Mr. DETR (Swin-L, 1x, 5cale))
    SOTA
    Dynamic Head: Unifying Object Detection Heads with AttentionsarXiv:2106.08322
  • 3DonCOCO 2017 val
    APL· 2021-06-15
    64.2
    best: 75.7 (Mr. DETR (Swin-L, 1x, 5cale))
    SOTA
    Dynamic Head: Unifying Object Detection Heads with AttentionsarXiv:2106.08322
  • 2D ClassificationonCOCO 2017 val
    AP50· 2021-06-15
    68
    best: 79 (Mr. DETR (Swin-L, 1x, 5cale))
    SOTA
    Dynamic Head: Unifying Object Detection Heads with AttentionsarXiv:2106.08322
  • 2D ClassificationonCOCO 2017 val
    AP75· 2021-06-15
    54.3
    best: 67.6 (Mr. DETR (Swin-L, 1x, 5cale))
    SOTA
    Dynamic Head: Unifying Object Detection Heads with AttentionsarXiv:2106.08322
  • 2D ClassificationonCOCO 2017 val
    APL· 2021-06-15
    64.2
    best: 75.7 (Mr. DETR (Swin-L, 1x, 5cale))
    SOTA
    Dynamic Head: Unifying Object Detection Heads with AttentionsarXiv:2106.08322
  • 2D Object DetectiononCOCO 2017 val
    AP50· 2021-06-15
    68
    best: 79 (Mr. DETR (Swin-L, 1x, 5cale))
    SOTA
    Dynamic Head: Unifying Object Detection Heads with AttentionsarXiv:2106.08322
  • 2D Object DetectiononCOCO 2017 val
    AP75· 2021-06-15
    54.3
    best: 67.6 (Mr. DETR (Swin-L, 1x, 5cale))
    SOTA
    Dynamic Head: Unifying Object Detection Heads with AttentionsarXiv:2106.08322
  • 2D Object DetectiononCOCO 2017 val
    APL· 2021-06-15
    64.2
    best: 75.7 (Mr. DETR (Swin-L, 1x, 5cale))
    SOTA
    Dynamic Head: Unifying Object Detection Heads with AttentionsarXiv:2106.08322
  • 16konCOCO 2017 val
    AP50· 2021-06-15
    68
    best: 79 (Mr. DETR (Swin-L, 1x, 5cale))
    SOTA
    Dynamic Head: Unifying Object Detection Heads with AttentionsarXiv:2106.08322
  • 16konCOCO 2017 val
    AP75· 2021-06-15
    54.3
    best: 67.6 (Mr. DETR (Swin-L, 1x, 5cale))
    SOTA
    Dynamic Head: Unifying Object Detection Heads with AttentionsarXiv:2106.08322
  • 16konCOCO 2017 val
    APL· 2021-06-15
    64.2
    best: 75.7 (Mr. DETR (Swin-L, 1x, 5cale))
    SOTA
    Dynamic Head: Unifying Object Detection Heads with AttentionsarXiv:2106.08322

Computer Vision3 results

  • Object DetectiononCOCO 2017 val
    AP50· 2021-06-15
    68
    best: 79 (Mr. DETR (Swin-L, 1x, 5cale))
    SOTA
    Dynamic Head: Unifying Object Detection Heads with AttentionsarXiv:2106.08322
  • Object DetectiononCOCO 2017 val
    AP75· 2021-06-15
    54.3
    best: 67.6 (Mr. DETR (Swin-L, 1x, 5cale))
    SOTA
    Dynamic Head: Unifying Object Detection Heads with AttentionsarXiv:2106.08322
  • Object DetectiononCOCO 2017 val
    APL· 2021-06-15
    64.2
    best: 75.7 (Mr. DETR (Swin-L, 1x, 5cale))
    SOTA
    Dynamic Head: Unifying Object Detection Heads with AttentionsarXiv:2106.08322