Tasks SotA Datasets Papers Methods Submit About

Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable Benchmarks All SotA Datasets Papers Methods

Community

Submit Results About

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Models/EPE-NAS (N=1000)

EPE-NAS (N=1000)

Reported on 16 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.

Methodology16 results

Neural Architecture SearchonNAS-Bench-201, ImageNet-16-120
Accuracy (Test)· 2021-02-16
41.84
best: 46.98 (CR-LSO)
EPE-NAS: Efficient Performance Estimation Without Training for Neural Architecture Search arXiv:2102.08099
Neural Architecture SearchonNAS-Bench-201, ImageNet-16-120
Search time (s)· 2021-02-16
206.2
best: 151200 (Local search)
EPE-NAS: Efficient Performance Estimation Without Training for Neural Architecture Search arXiv:2102.08099
Neural Architecture SearchonNAS-Bench-201, CIFAR-10
Accuracy (Test)· 2021-02-16
91.31
best: 94.37 (DiNAS)
EPE-NAS: Efficient Performance Estimation Without Training for Neural Architecture Search arXiv:2102.08099
Neural Architecture SearchonNAS-Bench-201, CIFAR-10
Accuracy (Val)· 2021-02-16
87.87
best: 91.61 (DiNAS)
EPE-NAS: Efficient Performance Estimation Without Training for Neural Architecture Search arXiv:2102.08099
Neural Architecture SearchonNAS-Bench-201, CIFAR-10
Search time (s)· 2021-02-16
206.2
best: 31010 (SETN)
EPE-NAS: Efficient Performance Estimation Without Training for Neural Architecture Search arXiv:2102.08099
Neural Architecture SearchonNAS-Bench-201, CIFAR-100
Accuracy (Test)· 2021-02-16
69.58
best: 73.51 (DiNAS)
EPE-NAS: Efficient Performance Estimation Without Training for Neural Architecture Search arXiv:2102.08099
Neural Architecture SearchonNAS-Bench-201, CIFAR-100
Accuracy (Val)· 2021-02-16
69.44
best: 73.49 (DiNAS)
EPE-NAS: Efficient Performance Estimation Without Training for Neural Architecture Search arXiv:2102.08099
Neural Architecture SearchonNAS-Bench-201, CIFAR-100
Search time (s)· 2021-02-16
206.2
best: 31010 (SETN)
EPE-NAS: Efficient Performance Estimation Without Training for Neural Architecture Search arXiv:2102.08099
AutoMLonNAS-Bench-201, ImageNet-16-120
Accuracy (Test)· 2021-02-16
41.84
best: 46.98 (CR-LSO)
EPE-NAS: Efficient Performance Estimation Without Training for Neural Architecture Search arXiv:2102.08099
AutoMLonNAS-Bench-201, ImageNet-16-120
Search time (s)· 2021-02-16
206.2
best: 151200 (Local search)
EPE-NAS: Efficient Performance Estimation Without Training for Neural Architecture Search arXiv:2102.08099
AutoMLonNAS-Bench-201, CIFAR-10
Accuracy (Test)· 2021-02-16
91.31
best: 94.37 (DiNAS)
EPE-NAS: Efficient Performance Estimation Without Training for Neural Architecture Search arXiv:2102.08099
AutoMLonNAS-Bench-201, CIFAR-10
Accuracy (Val)· 2021-02-16
87.87
best: 91.61 (DiNAS)
EPE-NAS: Efficient Performance Estimation Without Training for Neural Architecture Search arXiv:2102.08099
AutoMLonNAS-Bench-201, CIFAR-10
Search time (s)· 2021-02-16
206.2
best: 31010 (SETN)
EPE-NAS: Efficient Performance Estimation Without Training for Neural Architecture Search arXiv:2102.08099
AutoMLonNAS-Bench-201, CIFAR-100
Accuracy (Test)· 2021-02-16
69.58
best: 73.51 (DiNAS)
EPE-NAS: Efficient Performance Estimation Without Training for Neural Architecture Search arXiv:2102.08099
AutoMLonNAS-Bench-201, CIFAR-100
Accuracy (Val)· 2021-02-16
69.44
best: 73.49 (DiNAS)
EPE-NAS: Efficient Performance Estimation Without Training for Neural Architecture Search arXiv:2102.08099
AutoMLonNAS-Bench-201, CIFAR-100
Search time (s)· 2021-02-16
206.2
best: 31010 (SETN)
EPE-NAS: Efficient Performance Estimation Without Training for Neural Architecture Search arXiv:2102.08099