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 1–50 of 1915 papers

TitleStatusHype
DAMO-YOLO : A Report on Real-Time Object Detection DesignCode4
Efficient Automated Deep Learning for Time Series ForecastingCode4
Structured Pruning for Deep Convolutional Neural Networks: A surveyCode4
EfficientNet: Rethinking Model Scaling for Convolutional Neural NetworksCode3
Model-based Asynchronous Hyperparameter and Neural Architecture SearchCode3
EfficientNetV2: Smaller Models and Faster TrainingCode3
DNA Family: Boosting Weight-Sharing NAS with Block-Wise SupervisionsCode3
MobileNetV4 -- Universal Models for the Mobile EcosystemCode3
Multi-objective Asynchronous Successive HalvingCode3
AutoGluon-Tabular: Robust and Accurate AutoML for Structured DataCode3
AnalogNAS-Bench: A NAS Benchmark for Analog In-Memory ComputingCode2
Nix-TTS: Lightweight and End-to-End Text-to-Speech via Module-wise DistillationCode2
AutoShot: A Short Video Dataset and State-of-the-Art Shot Boundary DetectionCode2
GAN Compression: Efficient Architectures for Interactive Conditional GANsCode2
Auto-PyTorch Tabular: Multi-Fidelity MetaLearning for Efficient and Robust AutoDLCode2
Searching Efficient 3D Architectures with Sparse Point-Voxel ConvolutionCode2
Fine-Grained Stochastic Architecture SearchCode2
ZoomNAS: Searching for Whole-body Human Pose Estimation in the WildCode2
MorphNet: Fast & Simple Resource-Constrained Structure Learning of Deep NetworksCode2
ALBench: A Framework for Evaluating Active Learning in Object DetectionCode2
ProxylessNAS: Direct Neural Architecture Search on Target Task and HardwareCode2
UL-UNAS: Ultra-Lightweight U-Nets for Real-Time Speech Enhancement via Network Architecture SearchCode2
Neural Prompt SearchCode2
A Multi-objective Optimization Benchmark Test Suite for Real-time Semantic SegmentationCode2
AMC: AutoML for Model Compression and Acceleration on Mobile DevicesCode2
Proximal Policy Optimization AlgorithmsCode2
GC4NC: A Benchmark Framework for Graph Condensation on Node Classification with New InsightsCode2
From Tiny Machine Learning to Tiny Deep Learning: A SurveyCode2
Automated Deep Learning: Neural Architecture Search Is Not the EndCode2
Learning Efficient Convolutional Networks through Network SlimmingCode2
Combinatorial Optimization with Automated Graph Neural NetworksCode2
DeepCore: A Comprehensive Library for Coreset Selection in Deep LearningCode2
LiteTransformerSearch: Training-free Neural Architecture Search for Efficient Language ModelsCode2
Adaptive Guidance: Training-free Acceleration of Conditional Diffusion ModelsCode2
Evolutionary Computation in the Era of Large Language Model: Survey and RoadmapCode2
AutoSpeech: Neural Architecture Search for Speaker RecognitionCode1
AutoSNN: Towards Energy-Efficient Spiking Neural NetworksCode1
Bag of Baselines for Multi-objective Joint Neural Architecture Search and Hyperparameter OptimizationCode1
An Asymptotically Optimal Multi-Armed Bandit Algorithm and Hyperparameter OptimizationCode1
BANANAS: Bayesian Optimization with Neural Architectures for Neural Architecture SearchCode1
Discovering Neural WiringsCode1
Accelerating Neural Architecture Search via Proxy DataCode1
AutoPEFT: Automatic Configuration Search for Parameter-Efficient Fine-TuningCode1
Grafting Transformer on Automatically Designed Convolutional Neural Network for Hyperspectral Image ClassificationCode1
AutoReCon: Neural Architecture Search-based Reconstruction for Data-free CompressionCode1
Bayesian Model Selection, the Marginal Likelihood, and GeneralizationCode1
Adaptive Cross-Layer Attention for Image RestorationCode1
Automated Search for Resource-Efficient Branched Multi-Task NetworksCode1
Adaptive Linear Span Network for Object Skeleton DetectionCode1
Automatic Relation-aware Graph Network ProliferationCode1
Show:102550
← PrevPage 1 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