Neural Architecture Search On Cifar 10

评估指标

Parameters

Search Time (GPU days)

Top-1 Error Rate

评测结果

各个模型在此基准测试上的表现结果

模型名称	Parameters	Search Time (GPU days)	Top-1 Error Rate	Paper Title	Repository
CATE	4.1	10.3	2.46%	CATE: Computation-aware Neural Architecture Encoding with Transformers
EEEA-Net-C (b=5)+ CO	-	-	2.46%	EEEA-Net: An Early Exit Evolutionary Neural Architecture Search
NN-MASS- CIFAR-C	3.82M	0	3.18%	How does topology of neural architectures impact gradient propagation and model performance?
GDAS	-	0.21	3.4%	Searching for A Robust Neural Architecture in Four GPU Hours
NAO	144.6M	200	1.93%	-	-
μDARTS	-	0.1	3.277%	$μ$DARTS: Model Uncertainty-Aware Differentiable Architecture Search	-
Net2 (2)	-	-	3.3%	Efficacy of Neural Prediction-Based Zero-Shot NAS
NN-MASS- CIFAR-A	5.02M	0	3.0%	How does topology of neural architectures impact gradient propagation and model performance?
MUXNet-m	2.1M	-	2.0%	MUXConv: Information Multiplexing in Convolutional Neural Networks
ZenNet-2.0M	2.0M	-	2.5%	Zen-NAS: A Zero-Shot NAS for High-Performance Deep Image Recognition
DNA-c	-	-	1.7%	Blockwisely Supervised Neural Architecture Search with Knowledge Distillation	-
NAT-M1	4.3M	1.0	2.6%	Neural Architecture Transfer
Balanced Mixture	-	-	-	Balanced Mixture of SuperNets for Learning the CNN Pooling Architecture
FairDARTS-a	2.8M	0.25	2.54%	Fair DARTS: Eliminating Unfair Advantages in Differentiable Architecture Search	-
NAT-M4	6.9M	1.0	1.6%	Neural Architecture Transfer
SETN (T=1K) + CutOut	-	1.8	2.69%	One-Shot Neural Architecture Search via Self-Evaluated Template Network
TNASP	3.7M	0.3	2.52%	TNASP: A Transformer-based NAS Predictor with a Self-evolution Framework	-
DU-DARTS	3.8M	0.4	2.32%	DU-DARTS: Decreasing the Uncertainty of Differentiable Architecture Search
sharpDARTS	1.98M	1.8	2.29%	sharpDARTS: Faster and More Accurate Differentiable Architecture Search
NAT-M2	4.6M	1.0	2.1%	Neural Architecture Transfer

0 of 41 row(s) selected.