Neural Architecture Search On Cifar 100 1

Métriques

FLOPS

PARAMS

Percentage Error

Résultats

Résultats de performance de divers modèles sur ce benchmark

				Paper Title
μDARTS	-	602M	19.39	$μ$DARTS: Model Uncertainty-Aware Differentiable Architecture Search
NASGEP	-	-	18.83	Optimizing Neural Architecture Search using Limited GPU Time in a Dynamic Search Space: A Gene Expression Programming Approach
DARTS-PRIME	-	3.16M	17.44	DARTS-PRIME: Regularization and Scheduling Improve Constrained Optimization in Differentiable NAS
DU-DARTS	-	3.1M	16.74	DU-DARTS: Decreasing the Uncertainty of Differentiable Architecture Search
β-DARTS	-	-	16.52	$β$-DARTS: Beta-Decay Regularization for Differentiable Architecture Search
ZenNet-2.0M	487M	2.0M	15.6	Zen-NAS: A Zero-Shot NAS for High-Performance Deep Image Recognition
NAT-M1	261M	3.8M	14.0	Neural Architecture Transfer
MUXNet-m	200M	2.1M	13.9	MUXConv: Information Multiplexing in Convolutional Neural Networks
NAT-M2	398M	6.4M	12.5	Neural Architecture Transfer
NAT-M3	492M	7.8M	12.3	Neural Architecture Transfer
DNA-c	-	-	11.7	Blockwisely Supervised Neural Architecture Search with Knowledge Distillation
NAT-M4	796M	9.0M	11.7	Neural Architecture Transfer
Balanced Mixture	-	-	-	Balanced Mixture of SuperNets for Learning the CNN Pooling Architecture

0 of 13 row(s) selected.

Neural Architecture Search On Cifar 100 1 | SOTA | HyperAI