SOTAVerified

Neural Architecture Search

Neural architecture search (NAS) is a technique for automating the design of artificial neural networks (ANN), a widely used model in the field of machine learning. NAS essentially takes the process of a human manually tweaking a neural network and learning what works well, and automates this task to discover more complex architectures.

Image Credit : NAS with Reinforcement Learning

Papers

Showing 17511800 of 1915 papers

TitleStatusHype
EfficientNet: Rethinking Model Scaling for Convolutional Neural NetworksCode3
Dynamic Cell Structure via Recursive-Recurrent Neural Networks0
Network Pruning via Transformable Architecture SearchCode0
Adaptive Stochastic Natural Gradient Method for One-Shot Neural Architecture SearchCode0
DARC: Differentiable ARchitecture Compression0
Multinomial Distribution Learning for Effective Neural Architecture SearchCode0
AutoDispNet: Improving Disparity Estimation With AutoMLCode0
DeepSwarm: Optimising Convolutional Neural Networks using Swarm IntelligenceCode0
Regularized Evolutionary Algorithm for Dynamic Neural Topology Search0
Deep Neural Architecture Search with Deep Graph Bayesian OptimizationCode0
BayesNAS: A Bayesian Approach for Neural Architecture Search0
Dynamic Routing Networks0
Budgeted Training: Rethinking Deep Neural Network Training Under Resource ConstraintsCode0
EENA: Efficient Evolution of Neural ArchitectureCode0
Single-Path NAS: Device-Aware Efficient ConvNet Design0
Seesaw-Net: Convolution Neural Network With Uneven Group ConvolutionCode0
Efficient Neural Architecture Search on Low-Dimensional Data for OCT Image Segmentation0
Neural Architecture Refinement: A Practical Way for Avoiding Overfitting in NAS0
Searching for MobileNetV3Code1
Differentiable Architecture Search with Ensemble Gumbel-Softmax0
Fast and Reliable Architecture Selection for Convolutional Neural NetworksCode0
A Survey on Neural Architecture Search0
Probabilistic Model-Based Dynamic Architecture Search0
Single Shot Neural Architecture Search Via Direct Sparse Optimization0
AdaNet: A Scalable and Flexible Framework for Automatically Learning EnsemblesCode0
Progressive Differentiable Architecture Search: Bridging the Depth Gap between Search and EvaluationCode0
TreeGrad: Transferring Tree Ensembles to Neural NetworksCode0
D-VAE: A Variational Autoencoder for Directed Acyclic GraphsCode0
GraphNAS: Graph Neural Architecture Search with Reinforcement LearningCode0
Towards Learning of Filter-Level Heterogeneous Compression of Convolutional Neural NetworksCode0
Neural Architecture Search for Deep Face Recognition0
Language Models with TransformersCode0
NAS-FPN: Learning Scalable Feature Pyramid Architecture for Object DetectionCode0
Resource Constrained Neural Network Architecture Search: Will a Submodularity Assumption Help?Code0
ASAP: Architecture Search, Anneal and Prune0
WeNet: Weighted Networks for Recurrent Network Architecture Search0
Single-Path NAS: Designing Hardware-Efficient ConvNets in less than 4 HoursCode0
Branched Multi-Task Networks: Deciding What Layers To Share0
Architecture Search of Dynamic Cells for Semantic Video Segmentation0
Meta-learning Convolutional Neural Architectures for Multi-target Concrete Defect Classification with the COncrete DEfect BRidge IMage DatasetCode0
Exploring Randomly Wired Neural Networks for Image RecognitionCode0
Learn to Grow: A Continual Structure Learning Framework for Overcoming Catastrophic Forgetting0
Understanding Neural Architecture Search Techniques0
Single Path One-Shot Neural Architecture Search with Uniform SamplingCode1
AutoSlim: Towards One-Shot Architecture Search for Channel NumbersCode1
Deep Demosaicing for Edge Implementation0
AlphaX: eXploring Neural Architectures with Deep Neural Networks and Monte Carlo Tree SearchCode0
DetNAS: Backbone Search for Object DetectionCode0
Auto-ReID: Searching for a Part-aware ConvNet for Person Re-IdentificationCode0
sharpDARTS: Faster and More Accurate Differentiable Architecture SearchCode0
Show:102550
← PrevPage 36 of 39Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1SPOS (ProxylessNAS (GPU) latency)Accuracy75.3Unverified
2SPOS (FBNet-C latency)Accuracy75.1Unverified
3SPOS (block search + channel search)Accuracy74.7Unverified
4MUXNet-xsTop-1 Error Rate33.3Unverified
5FBNetV2-F1Top-1 Error Rate31.7Unverified
6LayerNAS-60MTop-1 Error Rate31Unverified
7NASGEPTop-1 Error Rate29.51Unverified
8MUXNet-sTop-1 Error Rate28.4Unverified
9NN-MASS-ATop-1 Error Rate27.1Unverified
10FBNetV2-F3Top-1 Error Rate26.8Unverified
#ModelMetricClaimedVerifiedStatus
1CR-LSOAccuracy (Test)46.98Unverified
2Shapley-NASAccuracy (Test)46.85Unverified
3β-SDARTS-RSAccuracy (Test)46.71Unverified
4β-RDARTS-L2Accuracy (Test)46.71Unverified
5NARAccuracy (Test)46.66Unverified
6ASE-NAS+Accuracy (Val)46.66Unverified
7BaLeNAS-TFAccuracy (Test)46.54Unverified
8AG-NetAccuracy (Test)46.42Unverified
9Local searchAccuracy (Test)46.38Unverified
10NASBOTAccuracy (Test)46.37Unverified
#ModelMetricClaimedVerifiedStatus
1Balanced MixtureAccuracy (% )91.55Unverified
2GDASTop-1 Error Rate3.4Unverified
3Bonsai-NetTop-1 Error Rate3.35Unverified
4Net2 (2)Top-1 Error Rate3.3Unverified
5μDARTSTop-1 Error Rate3.28Unverified
6NN-MASS- CIFAR-CTop-1 Error Rate3.18Unverified
7DARTS (first order)Top-1 Error Rate3Unverified
8NN-MASS- CIFAR-ATop-1 Error Rate3Unverified
9AlphaX-1 (cutout NASNet)Top-1 Error Rate2.82Unverified
10NASGEPTop-1 Error Rate2.82Unverified