DARTS-SaBN

Reported on 4 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.

Methodology4 results

Neural Architecture SearchonNAS-Bench-201, ImageNet-16-120
Accuracy (Test)· 2021-02-22
45.85
best: 46.98 (CR-LSO)
Sandwich Batch Normalization: A Drop-In Replacement for Feature Distribution Heterogeneity arXiv:2102.11382
Neural Architecture SearchonNAS-Bench-201, CIFAR-100
Accuracy (Test)· 2021-02-22
71.56
best: 73.51 (DiNAS)
Sandwich Batch Normalization: A Drop-In Replacement for Feature Distribution Heterogeneity arXiv:2102.11382
AutoMLonNAS-Bench-201, ImageNet-16-120
Accuracy (Test)· 2021-02-22
45.85
best: 46.98 (CR-LSO)
Sandwich Batch Normalization: A Drop-In Replacement for Feature Distribution Heterogeneity arXiv:2102.11382
AutoMLonNAS-Bench-201, CIFAR-100
Accuracy (Test)· 2021-02-22
71.56
best: 73.51 (DiNAS)
Sandwich Batch Normalization: A Drop-In Replacement for Feature Distribution Heterogeneity arXiv:2102.11382