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/CleanNet

CleanNet

Reported on 11 benchmarks across 6 tasks · 1 paper · 1 SOTA

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

Computer Vision9 results

  • Image ClassificationonFood-101N
    Accuracy· uses extra data· 2017-11-20
    90.39
    best: 93.42 (LRA-diffusion (CLIP ViT))
    SOTA
    CleanNet: Transfer Learning for Scalable Image Classifier Training with Label NoisearXiv:1711.07131
  • VideoonTHUMOS 2014
    mAP@0.5
    23.9
    best: 52.2 (HR-Pro)
  • VideoonActivityNet-1.2
    mAP@0.5
    37.1
    best: 49.6 (AICL)
  • Temporal Action LocalizationonTHUMOS 2014
    mAP@0.5
    23.9
    best: 52.2 (HR-Pro)
  • Temporal Action LocalizationonActivityNet-1.2
    mAP@0.5
    37.1
    best: 49.6 (AICL)
  • Action LocalizationonTHUMOS 2014
    mAP@0.5
    23.9
    best: 52.2 (HR-Pro)
  • Action LocalizationonActivityNet-1.2
    mAP@0.5
    37.1
    best: 49.6 (AICL)
  • Weakly Supervised Action LocalizationonTHUMOS 2014
    mAP@0.5
    23.9
    best: 52.2 (HR-Pro)
  • Weakly Supervised Action LocalizationonActivityNet-1.2
    mAP@0.5
    37.1
    best: 49.6 (AICL)

Methodology2 results

  • Zero-Shot LearningonTHUMOS 2014
    mAP@0.5
    23.9
    best: 52.2 (HR-Pro)
  • Zero-Shot LearningonActivityNet-1.2
    mAP@0.5
    37.1
    best: 49.6 (AICL)