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

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1101–1150 of 1915 papers

TitleStatusHype
Search to aggregate neighborhood for graph neural networkCode1
Neural Architecture Search of Deep Priors: Towards Continual Learning without Catastrophic InterferenceCode1
End-to-end Keyword Spotting using Neural Architecture Search and Quantization—0
Landmark Regularization: Ranking Guided Super-Net Training in Neural Architecture SearchCode0
Improved Conformer-based End-to-End Speech Recognition Using Neural Architecture Search—0
AutoGL: A Library for Automated Graph LearningCode1
Autoequivariant Network Search via Group DecompositionCode0
FL-AGCNS: Federated Learning Framework for Automatic Graph Convolutional Network Search—0
A Design Space Study for LISTA and Beyond—0
Partially-Connected Differentiable Architecture Search for Deepfake and Spoofing DetectionCode1
Searching Efficient Model-guided Deep Network for Image Denoising—0
How Powerful are Performance Predictors in Neural Architecture Search?—0
EfficientNetV2: Smaller Models and Faster TrainingCode3
One-Shot Neural Ensemble Architecture Search by Diversity-Guided Search Space ShrinkingCode1
NetAdaptV2: Efficient Neural Architecture Search with Fast Super-Network Training and Architecture Optimization—0
Joint Learning of Neural Transfer and Architecture Adaptation for Image Recognition—0
Differentiable Network Adaption with Elastic Search Space—0
A resource-efficient method for repeated HPO and NAS problems—0
DiNTS: Differentiable Neural Network Topology Search for 3D Medical Image SegmentationCode0
Rethinking Neural Operations for Diverse TasksCode1
Visionary: Vision architecture discovery for robot learning—0
Rethinking Graph Neural Architecture Search from Message-passingCode1
EfficientTDNN: Efficient Architecture Search for Speaker RecognitionCode1
Recovering Quantitative Models of Human Information Processing with Differentiable Architecture SearchCode0
MANAS: Multi-Scale and Multi-Level Neural Architecture Search for Low-Dose CT Denoising—0
Learning Versatile Neural Architectures by Propagating Network CodesCode1
Fisher Task Distance and Its Application in Neural Architecture SearchCode0
BossNAS: Exploring Hybrid CNN-transformers with Block-wisely Self-supervised Neural Architecture SearchCode1
Enhanced Gradient for Differentiable Architecture Search—0
AutoSpace: Neural Architecture Search with Less Human InterferenceCode0
Prioritized Architecture Sampling with Monto-Carlo Tree SearchCode1
MoViNets: Mobile Video Networks for Efficient Video RecognitionCode1
HW-NAS-Bench:Hardware-Aware Neural Architecture Search BenchmarkCode1
GPNAS: A Neural Network Architecture Search Framework Based on Graphical Predictor—0
NAS-TC: Neural Architecture Search on Temporal Convolutions for Complex Action Recognition—0
The Untapped Potential of Off-the-Shelf Convolutional Neural Networks—0
Pretraining Neural Architecture Search Controllers with Locality-based Self-Supervised LearningCode0
Neural Architecture Search based on Cartesian Genetic Programming Coding Method—0
Interleaving Learning, with Application to Neural Architecture Search—0
Learning by Teaching, with Application to Neural Architecture Search—0
HSCoNAS: Hardware-Software Co-Design of Efficient DNNs via Neural Architecture Search—0
Trainless Model Performance Estimation for Neural Architecture Search—0
Contrastive Neural Architecture Search with Neural Architecture ComparatorsCode1
OPANAS: One-Shot Path Aggregation Network Architecture Search for Object DetectionCode1
Efficient Model Performance Estimation via Feature Histories—0
Auto-tuning of Deep Neural Networks by Conflicting Layer RemovalCode0
Deep reinforcement learning in medical imaging: A literature review—0
Differentiable Neural Architecture Learning for Efficient Neural Network DesignCode1
Improving Neural Networks for Time Series Forecasting using Data Augmentation and AutoMLCode0
Task-Adaptive Neural Network Search with Meta-Contrastive LearningCode1
Show:102550
← PrevPage 23 of 39Next →
All datasetsImageNetNAS-Bench-201, ImageNet-16-120CIFAR-10NAS-Bench-201, CIFAR-100NAS-Bench-201, CIFAR-10CIFAR-10 Image ClassificationCIFAR-100NATS-Bench Topology, CIFAR-10NATS-Bench Topology, CIFAR-100NATS-Bench Topology, ImageNet16-120Food-101NAS-Bench-101

Benchmark Results

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