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/DU-DARTS

DU-DARTS

Reported on 18 benchmarks across 2 tasks

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

Methodology18 results

  • Neural Architecture SearchonNAS-Bench-201, ImageNet-16-120
    Accuracy (Test)
    45.94
    best: 46.98 (CR-LSO)
  • Neural Architecture SearchonNAS-Bench-201, CIFAR-10
    Accuracy (Test)
    93.86
    best: 94.37 (DiNAS)
  • Neural Architecture SearchonNAS-Bench-201, CIFAR-10
    Accuracy (Val)
    91.21
    best: 91.61 (DiNAS)
  • Neural Architecture SearchonCIFAR-100
    Percentage Error
    16.74
    best: 11.7 (DNA-c)
  • Neural Architecture SearchonCIFAR-10
    Search Time (GPU days)
    0.4
    best: 224 (AlphaX-1 (cutout NASNet))
  • Neural Architecture SearchonImageNet
    Accuracy
    75.9
    best: 83.9 (DeepMAD-50M)
  • Neural Architecture SearchonImageNet
    Top-1 Error Rate
    24.1
    best: 16.1 (DeepMAD-50M)
  • Neural Architecture SearchonNAS-Bench-201, CIFAR-100
    Accuracy (Test)
    71.84
    best: 73.51 (DiNAS)
  • Neural Architecture SearchonNAS-Bench-201, CIFAR-100
    Accuracy (Val)
    71.88
    best: 73.49 (DiNAS)
  • AutoMLonNAS-Bench-201, ImageNet-16-120
    Accuracy (Test)
    45.94
    best: 46.98 (CR-LSO)
  • AutoMLonNAS-Bench-201, CIFAR-10
    Accuracy (Test)
    93.86
    best: 94.37 (DiNAS)
  • AutoMLonNAS-Bench-201, CIFAR-10
    Accuracy (Val)
    91.21
    best: 91.61 (DiNAS)
  • AutoMLonCIFAR-100
    Percentage Error
    16.74
    best: 11.7 (DNA-c)
  • AutoMLonCIFAR-10
    Search Time (GPU days)
    0.4
    best: 224 (AlphaX-1 (cutout NASNet))
  • AutoMLonImageNet
    Accuracy
    75.9
    best: 83.9 (DeepMAD-50M)
  • AutoMLonImageNet
    Top-1 Error Rate
    24.1
    best: 16.1 (DeepMAD-50M)
  • AutoMLonNAS-Bench-201, CIFAR-100
    Accuracy (Test)
    71.84
    best: 73.51 (DiNAS)
  • AutoMLonNAS-Bench-201, CIFAR-100
    Accuracy (Val)
    71.88
    best: 73.49 (DiNAS)