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/RetinaNet (SpineNet-190, 1536x1536)

RetinaNet (SpineNet-190, 1536x1536)

Reported on 6 benchmarks across 6 tasks · 1 paper · 6 SOTA

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

Methodology4 results

  • 3DonCOCO minival
    box AP· 2019-12-10
    52.2
    best: 66 (PE_spatial (DETA))
    SOTA
    SpineNet: Learning Scale-Permuted Backbone for Recognition and LocalizationarXiv:1912.05027
  • 2D ClassificationonCOCO minival
    box AP· 2019-12-10
    52.2
    best: 66 (PE_spatial (DETA))
    SOTA
    SpineNet: Learning Scale-Permuted Backbone for Recognition and LocalizationarXiv:1912.05027
  • 2D Object DetectiononCOCO minival
    box AP· 2019-12-10
    52.2
    best: 66 (PE_spatial (DETA))
    SOTA
    SpineNet: Learning Scale-Permuted Backbone for Recognition and LocalizationarXiv:1912.05027
  • 16konCOCO minival
    box AP· 2019-12-10
    52.2
    best: 66 (PE_spatial (DETA))
    SOTA
    SpineNet: Learning Scale-Permuted Backbone for Recognition and LocalizationarXiv:1912.05027

Computer Vision2 results

  • Object DetectiononCOCO minival
    box AP· 2019-12-10
    52.2
    best: 66 (PE_spatial (DETA))
    SOTA
    SpineNet: Learning Scale-Permuted Backbone for Recognition and LocalizationarXiv:1912.05027
  • Instance SegmentationonCOCO minival
    mask AP· 2019-12-10
    46.1
    best: 56.6 (Co-DETR)
    SOTA
    SpineNet: Learning Scale-Permuted Backbone for Recognition and LocalizationarXiv:1912.05027