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 301–350 of 1915 papers

TitleStatusHype
GLiT: Neural Architecture Search for Global and Local Image TransformerCode1
Global Convergence of MAML and Theory-Inspired Neural Architecture Search for Few-Shot LearningCode1
GraTO: Graph Neural Network Framework Tackling Over-smoothing with Neural Architecture SearchCode1
Adjoined Networks: A Training Paradigm with Applications to Network CompressionCode1
HADAS: Hardware-Aware Dynamic Neural Architecture Search for Edge Performance ScalingCode1
HardCoRe-NAS: Hard Constrained diffeRentiable Neural Architecture SearchCode1
HAT: Hardware-Aware Transformers for Efficient Natural Language ProcessingCode1
BigNAS: Scaling Up Neural Architecture Search with Big Single-Stage ModelsCode1
Hierarchical Neural Architecture Search for Single Image Super-ResolutionCode1
Hierarchical Neural Architecture Search for Deep Stereo MatchingCode1
HW-GPT-Bench: Hardware-Aware Architecture Benchmark for Language ModelsCode1
BiX-NAS: Searching Efficient Bi-directional Architecture for Medical Image SegmentationCode1
A Study on Encodings for Neural Architecture SearchCode1
Block-Wisely Supervised Neural Architecture Search With Knowledge DistillationCode1
Blockwisely Supervised Neural Architecture Search with Knowledge DistillationCode1
iDARTS: Differentiable Architecture Search with Stochastic Implicit GradientsCode1
BM-NAS: Bilevel Multimodal Neural Architecture SearchCode1
BN-NAS: Neural Architecture Search with Batch NormalizationCode1
Contrastive Neural Architecture Search with Neural Architecture ComparatorsCode1
Knapsack Pruning with Inner DistillationCode1
ColdNAS: Search to Modulate for User Cold-Start RecommendationCode1
Learning Efficient, Explainable and Discriminative Representations for Pulmonary Nodules ClassificationCode1
Contrastive Embeddings for Neural ArchitecturesCode1
Learning Where To Look -- Generative NAS is Surprisingly EfficientCode1
BossNAS: Exploring Hybrid CNN-transformers with Block-wisely Self-supervised Neural Architecture SearchCode1
Bounce: Reliable High-Dimensional Bayesian Optimization for Combinatorial and Mixed SpacesCode1
ConvNet Architecture Search for Spatiotemporal Feature LearningCode1
Designing the Topology of Graph Neural Networks: A Novel Feature Fusion PerspectiveCode1
Local Search is a Remarkably Strong Baseline for Neural Architecture SearchCode1
Exploring the Loss Landscape in Neural Architecture SearchCode1
Breaking the Curse of Space Explosion: Towards Efficient NAS with Curriculum SearchCode1
Memory-Efficient Hierarchical Neural Architecture Search for Image RestorationCode1
Meta-prediction Model for Distillation-Aware NAS on Unseen DatasetsCode1
MicroNets: Neural Network Architectures for Deploying TinyML Applications on Commodity MicrocontrollersCode1
AIO-P: Expanding Neural Performance Predictors Beyond Image ClassificationCode1
Cross Task Neural Architecture Search for EEG Signal ClassificationsCode1
Adversarial Branch Architecture Search for Unsupervised Domain AdaptationCode1
AutoSpeech: Neural Architecture Search for Speaker RecognitionCode1
ChamNet: Towards Efficient Network Design through Platform-Aware Model AdaptationCode1
DHP: Differentiable Meta Pruning via HyperNetworksCode1
MPCViT: Searching for Accurate and Efficient MPC-Friendly Vision Transformer with Heterogeneous AttentionCode1
MSINet: Twins Contrastive Search of Multi-Scale Interaction for Object ReIDCode1
DrNAS: Dirichlet Neural Architecture SearchCode1
AtomNAS: Fine-Grained End-to-End Neural Architecture SearchCode1
Can GPT-4 Perform Neural Architecture Search?Code1
Efficient Neural Architecture Search for End-to-end Speech Recognition via Straight-Through GradientsCode1
Canvas: End-to-End Kernel Architecture Search in Neural NetworksCode1
Multi-Prior Learning via Neural Architecture Search for Blind Face RestorationCode1
Cyclic Differentiable Architecture SearchCode1
Firefly Neural Architecture Descent: a General Approach for Growing Neural NetworksCode1
Show:102550
← PrevPage 7 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