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/Sparse R-CNN

Sparse R-CNN

Reported on 17 benchmarks across 5 tasks · 2 papers · 1 SOTA

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

Methodology14 results

  • 2D Object DetectiononCeyMo
    mAP· 2020-11-25
    47.3
    best: 70.7 (TransMind)
    SOTA
    Sparse R-CNN: End-to-End Object Detection with Learnable ProposalsarXiv:2011.12450
  • 3DonManga109-s 15test
    COCO-style AP· uses extra data· 2021-03-25
    63.1
    best: 70.2 (YOLOX-L)
    USB: Universal-Scale Object Detection BenchmarkarXiv:2103.14027
  • 3DonUSB (Standard USB 1.0 protocol)
    mCAP· 2021-03-25
    44.6
    best: 52.1 (UniverseNet-20.08)
    USB: Universal-Scale Object Detection BenchmarkarXiv:2103.14027
  • 3DonWaymo 2D detection all_ns f0val
    COCO-style AP· uses extra data· 2021-03-25
    32.8
    best: 41.6 (YOLOX-L)
    USB: Universal-Scale Object Detection BenchmarkarXiv:2103.14027
  • 2D ClassificationonManga109-s 15test
    COCO-style AP· uses extra data· 2021-03-25
    63.1
    best: 70.2 (YOLOX-L)
    USB: Universal-Scale Object Detection BenchmarkarXiv:2103.14027
  • 2D ClassificationonUSB (Standard USB 1.0 protocol)
    mCAP· 2021-03-25
    44.6
    best: 52.1 (UniverseNet-20.08)
    USB: Universal-Scale Object Detection BenchmarkarXiv:2103.14027
  • 2D ClassificationonWaymo 2D detection all_ns f0val
    COCO-style AP· uses extra data· 2021-03-25
    32.8
    best: 41.6 (YOLOX-L)
    USB: Universal-Scale Object Detection BenchmarkarXiv:2103.14027
  • 2D Object DetectiononManga109-s 15test
    COCO-style AP· uses extra data· 2021-03-25
    63.1
    best: 70.2 (YOLOX-L)
    USB: Universal-Scale Object Detection BenchmarkarXiv:2103.14027
  • 2D Object DetectiononUSB (Standard USB 1.0 protocol)
    mCAP· 2021-03-25
    44.6
    best: 52.1 (UniverseNet-20.08)
    USB: Universal-Scale Object Detection BenchmarkarXiv:2103.14027
  • 2D Object DetectiononWaymo 2D detection all_ns f0val
    COCO-style AP· uses extra data· 2021-03-25
    32.8
    best: 41.6 (YOLOX-L)
    USB: Universal-Scale Object Detection BenchmarkarXiv:2103.14027
  • 16konManga109-s 15test
    COCO-style AP· uses extra data· 2021-03-25
    63.1
    best: 70.2 (YOLOX-L)
    USB: Universal-Scale Object Detection BenchmarkarXiv:2103.14027
  • 16konUSB (Standard USB 1.0 protocol)
    mCAP· 2021-03-25
    44.6
    best: 52.1 (UniverseNet-20.08)
    USB: Universal-Scale Object Detection BenchmarkarXiv:2103.14027
  • 16konWaymo 2D detection all_ns f0val
    COCO-style AP· uses extra data· 2021-03-25
    32.8
    best: 41.6 (YOLOX-L)
    USB: Universal-Scale Object Detection BenchmarkarXiv:2103.14027
  • 2D Object DetectiononSARDet-100K
    box mAP· 2020-11-25
    38.1
    best: 55.4 (DenoDet)
    Sparse R-CNN: End-to-End Object Detection with Learnable ProposalsarXiv:2011.12450

Computer Vision3 results

  • Object DetectiononManga109-s 15test
    COCO-style AP· uses extra data· 2021-03-25
    63.1
    best: 70.2 (YOLOX-L)
    USB: Universal-Scale Object Detection BenchmarkarXiv:2103.14027
  • Object DetectiononUSB (Standard USB 1.0 protocol)
    mCAP· 2021-03-25
    44.6
    best: 52.1 (UniverseNet-20.08)
    USB: Universal-Scale Object Detection BenchmarkarXiv:2103.14027
  • Object DetectiononWaymo 2D detection all_ns f0val
    COCO-style AP· uses extra data· 2021-03-25
    32.8
    best: 41.6 (YOLOX-L)
    USB: Universal-Scale Object Detection BenchmarkarXiv:2103.14027