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/PiFeNet

PiFeNet

Reported on 70 benchmarks across 7 tasks · 1 paper · 28 SOTA

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

Methodology44 results

  • 3DonKITTI Pedestrian Moderate
    Average Precision· 2021-12-31
    0.4671
    SOTA
    Accurate and Real-time 3D Pedestrian Detection Using an Efficient Attentive Pillar NetworkarXiv:2112.15458
  • 3DonKITTI Pedestrian Hard
    Average Precision· 2021-12-31
    0.4271
    SOTA
    Accurate and Real-time 3D Pedestrian Detection Using an Efficient Attentive Pillar NetworkarXiv:2112.15458
  • 3DonKITTI Pedestrian
    mAP· 2021-12-31
    0.486
    SOTA
    Accurate and Real-time 3D Pedestrian Detection Using an Efficient Attentive Pillar NetworkarXiv:2112.15458
  • 3DonKITTI Pedestrian Easy
    Average Precision· 2021-12-31
    0.5639
    SOTA
    Accurate and Real-time 3D Pedestrian Detection Using an Efficient Attentive Pillar NetworkarXiv:2112.15458
  • 2D ClassificationonKITTI Pedestrian Moderate
    Average Precision· 2021-12-31
    0.4671
    SOTA
    Accurate and Real-time 3D Pedestrian Detection Using an Efficient Attentive Pillar NetworkarXiv:2112.15458
  • 2D ClassificationonKITTI Pedestrian Hard
    Average Precision· 2021-12-31
    0.4271
    SOTA
    Accurate and Real-time 3D Pedestrian Detection Using an Efficient Attentive Pillar NetworkarXiv:2112.15458
  • 2D ClassificationonKITTI Pedestrian
    mAP· 2021-12-31
    0.486
    SOTA
    Accurate and Real-time 3D Pedestrian Detection Using an Efficient Attentive Pillar NetworkarXiv:2112.15458
  • 2D ClassificationonKITTI Pedestrian Easy
    Average Precision· 2021-12-31
    0.5639
    SOTA
    Accurate and Real-time 3D Pedestrian Detection Using an Efficient Attentive Pillar NetworkarXiv:2112.15458
  • 2D Object DetectiononKITTI Pedestrian Moderate
    Average Precision· 2021-12-31
    0.4671
    SOTA
    Accurate and Real-time 3D Pedestrian Detection Using an Efficient Attentive Pillar NetworkarXiv:2112.15458
  • 2D Object DetectiononKITTI Pedestrian Hard
    Average Precision· 2021-12-31
    0.4271
    SOTA
    Accurate and Real-time 3D Pedestrian Detection Using an Efficient Attentive Pillar NetworkarXiv:2112.15458
  • 2D Object DetectiononKITTI Pedestrian
    mAP· 2021-12-31
    0.486
    SOTA
    Accurate and Real-time 3D Pedestrian Detection Using an Efficient Attentive Pillar NetworkarXiv:2112.15458
  • 2D Object DetectiononKITTI Pedestrian Easy
    Average Precision· 2021-12-31
    0.5639
    SOTA
    Accurate and Real-time 3D Pedestrian Detection Using an Efficient Attentive Pillar NetworkarXiv:2112.15458
  • 16konKITTI Pedestrian Moderate
    Average Precision· 2021-12-31
    0.4671
    SOTA
    Accurate and Real-time 3D Pedestrian Detection Using an Efficient Attentive Pillar NetworkarXiv:2112.15458
  • 16konKITTI Pedestrian Hard
    Average Precision· 2021-12-31
    0.4271
    SOTA
    Accurate and Real-time 3D Pedestrian Detection Using an Efficient Attentive Pillar NetworkarXiv:2112.15458
  • 16konKITTI Pedestrian
    mAP· 2021-12-31
    0.486
    SOTA
    Accurate and Real-time 3D Pedestrian Detection Using an Efficient Attentive Pillar NetworkarXiv:2112.15458
  • 16konKITTI Pedestrian Easy
    Average Precision· 2021-12-31
    0.5639
    SOTA
    Accurate and Real-time 3D Pedestrian Detection Using an Efficient Attentive Pillar NetworkarXiv:2112.15458
  • 3DonnuScenes
    NDS
    0.61
    best: 55.3 (LabelDistill)
  • 3DonnuScenes
    mAAE
    0.13
    best: 1 (BirdNet+ (multisweep))
  • 3DonnuScenes
    mAOE
    0.38
    best: 1.6 (PointNet)
  • 3DonnuScenes
    mAP
    0.48
    best: 45.1 (LabelDistill)
  • 3DonnuScenes
    mASE
    0.25
    best: 1 (qww)
  • 3DonnuScenes
    mATE
    0.32
    best: 1.06 (3D-GCK)
  • 3DonnuScenes
    mAVE
    0.26
    best: 2.21 (PointNet)
  • 2D ClassificationonnuScenes
    NDS
    0.61
    best: 55.3 (LabelDistill)
  • 2D ClassificationonnuScenes
    mAAE
    0.13
    best: 1 (BirdNet+ (multisweep))
  • 2D ClassificationonnuScenes
    mAOE
    0.38
    best: 1.6 (PointNet)
  • 2D ClassificationonnuScenes
    mAP
    0.48
    best: 45.1 (LabelDistill)
  • 2D ClassificationonnuScenes
    mASE
    0.25
    best: 1 (qww)
  • 2D ClassificationonnuScenes
    mATE
    0.32
    best: 1.06 (3D-GCK)
  • 2D ClassificationonnuScenes
    mAVE
    0.26
    best: 2.21 (PointNet)
  • 2D Object DetectiononnuScenes
    NDS
    0.61
    best: 55.3 (LabelDistill)
  • 2D Object DetectiononnuScenes
    mAAE
    0.13
    best: 1 (BirdNet+ (multisweep))
  • 2D Object DetectiononnuScenes
    mAOE
    0.38
    best: 1.6 (PointNet)
  • 2D Object DetectiononnuScenes
    mAP
    0.48
    best: 45.1 (LabelDistill)
  • 2D Object DetectiononnuScenes
    mASE
    0.25
    best: 1 (qww)
  • 2D Object DetectiononnuScenes
    mATE
    0.32
    best: 1.06 (3D-GCK)
  • 2D Object DetectiononnuScenes
    mAVE
    0.26
    best: 2.21 (PointNet)
  • 16konnuScenes
    NDS
    0.61
    best: 55.3 (LabelDistill)
  • 16konnuScenes
    mAAE
    0.13
    best: 1 (BirdNet+ (multisweep))
  • 16konnuScenes
    mAOE
    0.38
    best: 1.6 (PointNet)
  • 16konnuScenes
    mAP
    0.48
    best: 45.1 (LabelDistill)
  • 16konnuScenes
    mASE
    0.25
    best: 1 (qww)
  • 16konnuScenes
    mATE
    0.32
    best: 1.06 (3D-GCK)
  • 16konnuScenes
    mAVE
    0.26
    best: 2.21 (PointNet)

Computer Vision26 results

  • Object DetectiononKITTI Pedestrian Moderate
    Average Precision· 2021-12-31
    0.4671
    SOTA
    Accurate and Real-time 3D Pedestrian Detection Using an Efficient Attentive Pillar NetworkarXiv:2112.15458
  • Object DetectiononKITTI Pedestrian Hard
    Average Precision· 2021-12-31
    0.4271
    SOTA
    Accurate and Real-time 3D Pedestrian Detection Using an Efficient Attentive Pillar NetworkarXiv:2112.15458
  • Object DetectiononKITTI Pedestrian
    mAP· 2021-12-31
    0.486
    SOTA
    Accurate and Real-time 3D Pedestrian Detection Using an Efficient Attentive Pillar NetworkarXiv:2112.15458
  • Object DetectiononKITTI Pedestrian Easy
    Average Precision· 2021-12-31
    0.5639
    SOTA
    Accurate and Real-time 3D Pedestrian Detection Using an Efficient Attentive Pillar NetworkarXiv:2112.15458
  • Birds Eye View Object DetectiononKITTI Pedestrian Easy
    Average Precision· 2021-12-31
    0.6325
    SOTA
    Accurate and Real-time 3D Pedestrian Detection Using an Efficient Attentive Pillar NetworkarXiv:2112.15458
  • Birds Eye View Object DetectiononKITTI Pedestrian Moderate
    Average Precision· 2021-12-31
    0.5392
    SOTA
    Accurate and Real-time 3D Pedestrian Detection Using an Efficient Attentive Pillar NetworkarXiv:2112.15458
  • Birds Eye View Object DetectiononKITTI Pedestrian Hard
    Average Precision· 2021-12-31
    0.5053
    SOTA
    Accurate and Real-time 3D Pedestrian Detection Using an Efficient Attentive Pillar NetworkarXiv:2112.15458
  • Birds Eye View Object DetectiononKITTI Pedestrian
    mAP· 2021-12-31
    0.559
    SOTA
    Accurate and Real-time 3D Pedestrian Detection Using an Efficient Attentive Pillar NetworkarXiv:2112.15458
  • 3D Object DetectiononKITTI Pedestrian Moderate
    Average Precision· 2021-12-31
    0.4671
    SOTA
    Accurate and Real-time 3D Pedestrian Detection Using an Efficient Attentive Pillar NetworkarXiv:2112.15458
  • 3D Object DetectiononKITTI Pedestrian Hard
    Average Precision· 2021-12-31
    0.4271
    SOTA
    Accurate and Real-time 3D Pedestrian Detection Using an Efficient Attentive Pillar NetworkarXiv:2112.15458
  • 3D Object DetectiononKITTI Pedestrian
    mAP· 2021-12-31
    0.486
    SOTA
    Accurate and Real-time 3D Pedestrian Detection Using an Efficient Attentive Pillar NetworkarXiv:2112.15458
  • 3D Object DetectiononKITTI Pedestrian Easy
    Average Precision· 2021-12-31
    0.5639
    SOTA
    Accurate and Real-time 3D Pedestrian Detection Using an Efficient Attentive Pillar NetworkarXiv:2112.15458
  • Object DetectiononnuScenes
    NDS
    0.61
    best: 55.3 (LabelDistill)
  • Object DetectiononnuScenes
    mAAE
    0.13
    best: 1 (BirdNet+ (multisweep))
  • Object DetectiononnuScenes
    mAOE
    0.38
    best: 1.6 (PointNet)
  • Object DetectiononnuScenes
    mAP
    0.48
    best: 45.1 (LabelDistill)
  • Object DetectiononnuScenes
    mASE
    0.25
    best: 1 (qww)
  • Object DetectiononnuScenes
    mATE
    0.32
    best: 1.06 (3D-GCK)
  • Object DetectiononnuScenes
    mAVE
    0.26
    best: 2.21 (PointNet)
  • 3D Object DetectiononnuScenes
    NDS
    0.61
    best: 55.3 (LabelDistill)
  • 3D Object DetectiononnuScenes
    mAAE
    0.13
    best: 1 (BirdNet+ (multisweep))
  • 3D Object DetectiononnuScenes
    mAOE
    0.38
    best: 1.6 (PointNet)
  • 3D Object DetectiononnuScenes
    mAP
    0.48
    best: 45.1 (LabelDistill)
  • 3D Object DetectiononnuScenes
    mASE
    0.25
    best: 1 (qww)
  • 3D Object DetectiononnuScenes
    mATE
    0.32
    best: 1.06 (3D-GCK)
  • 3D Object DetectiononnuScenes
    mAVE
    0.26
    best: 2.21 (PointNet)