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/CATCH-meta

CATCH-meta

Reported on 8 benchmarks across 2 tasks · 1 paper

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

Methodology8 results

  • Neural Architecture SearchonNAS-Bench-201, ImageNet-16-120
    Accuracy (Val)· 2020-07-18
    46.07
    best: 46.73 (AG-Net)
    CATCH: Context-based Meta Reinforcement Learning for Transferrable Architecture SearcharXiv:2007.09380
  • Neural Architecture SearchonNAS-Bench-201, ImageNet-16-120
    Search time (s)· 2020-07-18
    18000
    best: 151200 (Local search)
    CATCH: Context-based Meta Reinforcement Learning for Transferrable Architecture SearcharXiv:2007.09380
  • Neural Architecture SearchonNAS-Bench-201, CIFAR-10
    Accuracy (Val)· 2020-07-18
    91.33
    best: 91.61 (DiNAS)
    CATCH: Context-based Meta Reinforcement Learning for Transferrable Architecture SearcharXiv:2007.09380
  • Neural Architecture SearchonNAS-Bench-201, CIFAR-100
    Accuracy (Val)· 2020-07-18
    72.57
    best: 73.49 (DiNAS)
    CATCH: Context-based Meta Reinforcement Learning for Transferrable Architecture SearcharXiv:2007.09380
  • AutoMLonNAS-Bench-201, ImageNet-16-120
    Accuracy (Val)· 2020-07-18
    46.07
    best: 46.73 (AG-Net)
    CATCH: Context-based Meta Reinforcement Learning for Transferrable Architecture SearcharXiv:2007.09380
  • AutoMLonNAS-Bench-201, ImageNet-16-120
    Search time (s)· 2020-07-18
    18000
    best: 151200 (Local search)
    CATCH: Context-based Meta Reinforcement Learning for Transferrable Architecture SearcharXiv:2007.09380
  • AutoMLonNAS-Bench-201, CIFAR-10
    Accuracy (Val)· 2020-07-18
    91.33
    best: 91.61 (DiNAS)
    CATCH: Context-based Meta Reinforcement Learning for Transferrable Architecture SearcharXiv:2007.09380
  • AutoMLonNAS-Bench-201, CIFAR-100
    Accuracy (Val)· 2020-07-18
    72.57
    best: 73.49 (DiNAS)
    CATCH: Context-based Meta Reinforcement Learning for Transferrable Architecture SearcharXiv:2007.09380