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 1651–1700 of 1915 papers

TitleStatusHype
SGAS: Sequential Greedy Architecture SearchCode0
Towards Oracle Knowledge Distillation with Neural Architecture Search—0
Fair DARTS: Eliminating Unfair Advantages in Differentiable Architecture SearchCode0
Ranking architectures using meta-learning—0
When NAS Meets Robustness: In Search of Robust Architectures against Adversarial AttacksCode0
Binarized Neural Architecture Search—0
Exploiting Operation Importance for Differentiable Neural Architecture Search—0
SM-NAS: Structural-to-Modular Neural Architecture Search for Object Detection—0
Measuring Uncertainty through Bayesian Learning of Deep Neural Network StructureCode0
Data Proxy Generation for Fast and Efficient Neural Architecture Search—0
AutoShrink: A Topology-aware NAS for Discovering Efficient Neural ArchitectureCode0
Bridging the Gap between Sample-based and One-shot Neural Architecture Search with BONAS—0
Search to Distill: Pearls are Everywhere but not the Eyes—0
Hybrid Composition with IdleBlock: More Efficient Networks for Image Recognition—0
ImmuNeCS: Neural Committee Search by an Artificial Immune System—0
Fine-Grained Neural Architecture Search—0
Automatic Design of CNNs via Differentiable Neural Architecture Search for PolSAR Image Classification—0
S2DNAS:Transforming Static CNN Model for Dynamic Inference via Neural Architecture Search—0
Neural Architecture Search for Natural Language Understanding—0
Learning Graph Convolutional Network for Skeleton-based Human Action Recognition by Neural SearchingCode0
Learning to reinforcement learn for Neural Architecture SearchCode0
RAPDARTS: Resource-Aware Progressive Differentiable Architecture Search—0
Auptimizer -- an Extensible, Open-Source Framework for Hyperparameter TuningCode0
Improved Differentiable Architecture Search for Language Modeling and Named Entity RecognitionCode0
On Neural Architecture Search for Resource-Constrained Hardware Platforms—0
Device-Circuit-Architecture Co-Exploration for Computing-in-Memory Neural Accelerators—0
Stabilizing DARTS with Amended Gradient Estimation on Architectural ParametersCode0
Fast Hardware-Aware Neural Architecture Search—0
Efficient Decoupled Neural Architecture Search by Structure and Operation SamplingCode0
NASIB: Neural Architecture Search withIn Budget—0
Structural Analysis of Sparse Neural Networks—0
One-Shot Neural Architecture Search via Self-Evaluated Template NetworkCode0
Improving One-shot NAS by Suppressing the Posterior Fading—0
Fast and Practical Neural Architecture SearchCode0
Sub-Architecture Ensemble Pruning in Neural Architecture SearchCode0
Blending Diverse Physical Priors with Neural NetworksCode0
Auto-FPN: Automatic Network Architecture Adaptation for Object Detection Beyond Classification—0
Towards modular and programmable architecture searchCode0
A Quantile-based Approach for Hyperparameter Transfer Learning—0
Exascale Deep Learning to Accelerate Cancer Research—0
Hierarchical Neural Architecture Search via Operator ClusteringCode0
Resizable Neural Networks—0
Filter redistribution templates for iteration-lessconvolutional model reduction—0
Scaling Up Neural Architecture Search with Big Single-Stage Models—0
Reinforcement Learning with Chromatic Networks—0
BANANAS: Bayesian Optimization with Neural Networks for Neural Architecture Search—0
Boosting Network: Learn by Growing Filters and Layers via SplitLBI—0
Neural Operator Search—0
Evo-NAS: Evolutionary-Neural Hybrid Agent for Architecture Search—0
CNAS: Channel-Level Neural Architecture Search—0
Show:102550
← PrevPage 34 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