MXD6 / Awesome-NAS-AMC

This repo is a survey for: Neural Architecture Search & Auto Model Compress

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Awesome-NAS-AMC

This repo is a survey for: Neural Architecture Search & Auto Model Compress

AutoML

Survey

  • 2021 AutoML:A Survey of the State-of-the-Art
  • 2021 AutoML:From Methodology to Application

一、Neural Architecture Search

1.Survey

  • 2019 Neural architecture search:A survey.pdf
  • 2021 A Survey on Evolutionary Neural Architecture Search.pdf
  • 2021 深度神经网络结构搜索综述.pdf
  • 2020 A Comprehensive Survey of Neural Architecture Search Challenges and Solutions.pdf

2.Method

  • 2017 Connectivity Learning in Multi-Branch Networks.pdf
  • 2017 Genetic cnn.pdf
  • 2017 Large-scale evolution of Image Classifiers.pdf
  • 2017 MetaQnn:Designing neural network architectures using reinforcement learning.pdf
  • 2017 N2N Learning:Network to network compression via policy gradient reinforcement learning.pdf
  • 2017 NASH-Net:Simple and efficient architecture search for convolutional neural networks.pdf
  • 2017 Neural architecture search with reinforcement learning.pdf
  • 2017 SMASH:One-Shot Model Architecture Search through HyperNetworks.pdf
  • 2018 BlockQNN:Efficient block-wise neural network architecture generation.pdf
  • 2018 DAS:Differentiable Neural Network Architecture Search.pdf
  • 2018 DPP-Net:Device-aware progressive search for Pareto-optimal Neural Architectures.pdf
  • 2018 EAS:Efficient architecture search by network transformation.pdf
  • 2018 ENAS:Efficient neural architecture search via Parameter sharing.pdf
  • 2018 Hierarchical-EAS:Hierarchical representations for efficient architecture search.pdf
  • 2018 Learning time memory-efficient deep architectures with budgeted super networks.pdf
  • 2018 Maskconnect:Connectivity learning by gradient descent.pdf
  • 2018 Morphnet:Fast & simple resource-constrained structure learning of Deep Networks.pdf
  • 2018 NASNet:Learning transferable architectures for scalable image recognition.pdf
  • 2018 Netadapt:Platform-aware neural network adaptation for mobile applications.pdf
  • 2018 Path-level EAS:Path-level network transformation for Efficient Architecture Search.pdf
  • 2018 PNAS:Progressive neural architecture search.pdf
  • 2018 Practical block-wise neural network architecture generation.pdf
  • 2018 Understanding and simplifying one-shot architecture search.pdf
  • 2019 Auto-Keras:An efficient neural architecture search system.pdf
  • 2019 AutoDispNet:Improving disparity estimation with AutoML.pdf
  • 2019 AutoSlim:Towards One-Shot Architecture Search for Channel Numbers.pdf
  • 2019 CAS:Continual and multi-task architecture search.pdf
  • 2019 ChamNet:Towards Efficient Network Design Through Platform-Aware Model Adaptation.pdf
  • 2019 DARTS:Differentiable architecture search.pdf
  • 2019 DATA:Differentiable ArchiTecture Approximation.pdf
  • 2019 Deep neural network architecture search using network morphism.pdf
  • 2019 Efficient multi-objective neural architecture search via lamarckian evolution.pdf
  • 2019 Efficientnet:Rethinking Model Scaling for Convolutional Neural Networks.pdf
  • 2019 Evaluating the search phase of neural architecture search.pdf
  • 2019 Fbnet:Hardware-aware efficient convnet design via differentiable neural architecture search.pdf
  • 2019 FPNAS:Fast and practical neural architecture search.pdf
  • 2019 GDAS:Searching for a Robust Neural Architecture in Four GPU Hours.pdf
  • 2019 Graph HyperNetworks for Neural Architecture Search.pdf
  • 2019 MdeNAS:Multinomial distribution learning for effective neural architecture search.pdf
  • 2019 MnasNet:Platform-Aware Neural Architecture Search for Mobile.pdf
  • 2019 Neural Architecture Optimization.pdf
  • 2019 On Neural Architecture Search for Resource-Constrained Hardware Platforms.pdf
  • 2019 On-Device Image Classification with Proxyless Neural Architecture Search and Quantization-Aware Fine-tuning.pdf
  • 2019 Once for all:Train one network and specialize it for efficient deployment.pdf
  • 2019 P-DARTS:Progressive differentiable architecture search:Bridging the Depth Gap between Search and Evaluation.pdf
  • 2019 Pc-DARTS:Partial channel connections for memory-efficient architecture search.pdf
  • 2019 ProxylessNAS:Direct Neural Architecture Search on Target Task and Hardware.pdf
  • 2019 Regularized evolution for image classifier architecture search.pdf
  • 2019 S2DNAS:Transforming Static CNN Model for Dynamic Inference via Neural Architecture Search.pdf
  • 2019 Searching for MobileNetV3.pdf
  • 2019 SETN:One-shot neural architecture search via self-evaluated template network.pdf
  • 2019 Single path one-shot neural architecture search with uniform sampling.pdf
  • 2019 Single-path nas:Designing hardware-efficient convnets in less than 4 hours.pdf
  • 2019 Snas:stochastic neural architecture search.pdf
  • 2019 SpArSe:Sparse Architecture Search for CNNs on Resource-Constrained Microcontrollers.pdf
  • 2019 XNAS:Neural Architecture Search with Expert Advice.pdf
  • 2019 You only search once:Single shot neural architecture search via direct sparse optimization.pdf
  • 2020 AutoML for Architecting Efficient and Specialized Neural Networks.pdf
  • 2020 AutoML-Zero:Evolving Machine Learning Algorithms From Scratch.pdf
  • 2020 BigNAS:Scaling up neural architecture search with big single-stage models.pdf
  • 2020 Block-wisely Supervised Neural Architecture Search with Knowledge Distillation.pdf
  • 2020 BRP-NAS:Prediction-based NAS using GCNs.pdf
  • 2020 Can weight sharing outperform random architecture search?An investigation with TuNAS.pdf
  • 2020 CARS:Continuous evolution for efficient neural architecture search.pdf
  • 2020 CNNPruner:Pruning Convolutional Neural Networks with Visual Analytics.pdf
  • 2020 Densely connected search space for more flexible neural architecture search.pdf
  • 2020 FNA:Fast neural network adaptation via parameter remapping and architecture search.pdf
  • 2020 GDAS-NSAS:Overcoming multi-model forgetting in one-shot NAS with diversity maximization.pdf
  • 2020 HAT:Hardware-Aware Transformers for Efficient Natural Language Processing.pdf
  • 2020 Improving one-shot NAS by suppressing the Posterior Fading.pdf
  • 2020 Learning Transferable Architectures for Scalable Image Recognition.pdf
  • 2020 MANAS:Multi-Agent Neural Architecture Search.pdf
  • 2020 MCUNet:Tiny Deep Learning on IoT Devices.pdf
  • 2020 MicroNets:NEURAL NETWORK ARCHITECTURES FOR DEPLOYING TINYML APPLICATIONS ON COMMODITY MICROCONTROLLERS.pdf
  • 2020 MoGA:Searching Beyond MobileNetV3.pdf
  • 2020 NAS-FCOS:Fast Neural Architecture Search for Object Detection.pdf
  • 2020 Neural architecture search in a proxy validation loss landscape.pdf
  • 2020 On Hyperparameter Optimization of Machine Learning Algorithms Theory and Practice.pdf
  • 2020 RandomNAS:Random search and reproducibility for neural architecture search.pdf
  • 2020 Semi-supervised neural architecture search.pdf
  • 2020 SGAS:Sequential greedy architecture search.pdf
  • 2020 SmoothDARTS:Stabilizing Differentiable Architecture Search via Perturbation-based Regularization.pdf
  • 2020 Sparse CNN Architecture Search (SCAS).pdf
  • 2020 Understanding and Robustifying Differentiable Architecture Search.pdf
  • 2021 A Data-driven Approach to Neural Network Architecture Initialization.pdf
  • 2021 A Two-Stage Efficient Evolutionary Neural Architecture Search Method for Image Classification.pdf
  • 2021 Approximate Neural Architecture Search via Operation Distribution Learning.pdf
  • 2021 BNAS v2:Learning Architectures for Binary Networks with Empirical Improvements.pdf
  • 2021 Discovering multi-hardware mobile models via architecture search.pdf
  • 2021 EC-DARTS:Inducing Equalized and Consistent Optimization into DARTS.pdf
  • 2021 EPE-NAS:Efficient Performance Estimation Without Training for Neural Architecture Search.pdf
  • 2021 FairNAS:Rethinking evaluation fairness of weight sharing neural architecture search.pdf
  • 2021 Fitting the search space of weight-sharing NAS with A Graph Convolutional Networks.pdf
  • 2021 FNAS:Uncertainty-Aware Fast Neural Architecture.pdf
  • 2021 Graph-based Neural Architecture Search with Operation Embeddings.pdf
  • 2021 Guided Evolution for Neural Architecture Search.pdf
  • 2021 HourNAS:Extremely Fast Neural Architecture Search Through an Hourglass Lens.pdf
  • 2021 MCUNetV2:Memory-Efficient Patch-based Inference for Tiny Deep Learning.pdf
  • 2021 MEMA-NAS:Memory-Efficient Multi-Agent Neural Architecture Search.pdf
  • 2021 MIGO-NAS:Towards Fast and Generalizable Neural Architecture Search.pdf
  • 2021 NATS-Bench:Benchmarking NAS Algorithms for Architecture Topology and Size.pdf
  • 2021 Neural Architecture Search on ImageNet in Four GPU Hours:A Theoretically Inspired Perspective.pdf
  • 2021 Neural Architecture Search without Training.pdf
  • 2021 Neural Architecture Tuning with Policy Adaptation.pdf
  • 2021 Not All Operations Contribute Equally:Hierarchical Operation-adaptive Predictor for Neural Architecture Search.pdf
  • 2021 One Proxy Device Is Enough for Hardware-Aware Neural Architecture Search.pdf
  • 2021 Parameter Prediction for Unseen Deep Architectures.pdf
  • 2021 ProxyBO:Accelerating Neural Architecture Search via Bayesian Optimization with Zero-cost Proxies.pdf
  • 2021 Supplementary of “FairNAS:Rethinking Evaluation Fairness of Weight Sharing Neural Architecture Search.pdf
  • 2021 TND-NAS:Towards Non-differentiable Objectives in Progressive Differentiable NAS Framework.pdf
  • 2021 UniNet:Unified Architecture Search with Convolution, Transformer, and MLP.pdf
  • 2021 Weight-Sharing Neural Architecture Search:A Battle to Shrink the Optimization Gap.pdf
  • 2021 Zen-NAS:A Zero Shot NAS for High Performance Image Recognition.pdf
  • 2021 Zero-Cost Proxies for LightWeight NAS.pdf
  • 2021 μNAS:Constrained Neural Architecture Search for Microcontrollers.pdf

3.Benchmark:

2019 NAS-Bench-101:Towards Reproducible Neural Architecture Search.pdf
2021 NAS-HPO-Bench-II:A Benchmark Dataset on Joint Optimization of Convolutional Neural Network Architecture and Training Hyperparameters.pdf

4.Application in other fields:

2019 Auto-deeplab:Hierarchical neural architecture search for Semantic Image Segmentation.pdf
2019 Auto-FPN:Automatic Network Architecture Adaptation for Object Detection Beyond Classification.pdf
2019 AutoGAN:Neural architecture search for generative adversarial networks.pdf
2019 Fast Neural Architecture Search of Compact Semantic Segmentation Models via Auxiliary Cells.pdf
2020 Searching Efficient 3D Architectures with Sparse Point-Voxel Convolution.pdf
2021 AutoFormer:Searching Transformers for Visual Recognition.pdf
2021 AutoNLU:Architecture Search for Sentence and Cross-sentence Attention Modeling with Re-designed Search Space.pdf
2021 Learning a Robust Part-Aware Monocular 3D Human Pose Estimator via Neural Architecture Search.pdf
2021 Object Point Cloud Classification via Poly-Convolutional Architecture Search.pdf
2021 Pyramid Architecture Search for Real-Time Image Deblurring.pdf

二、Hyperparameter Optimization:

三、Auto Model Compress

1.Survey

2.Method

2017 N2N learning:Network to Network Compression Via Policy Gradient Reinforcement Learning.pdf
2018 AMC:AutoML for Model Compression and Acceleration on Mobile Devices.pdf
2018 Layer-compensated pruning for resource-constrained convolutional neural networks.pdf
2018 Learning to Prune Filters in Convolutional Neural Networks.pdf
2018 Netadapt:Platform-Aware Neural Network Adaptation for Mobile Applications.pdf
2019 AutoPruner:An End-to-End Trainable Filter Pruning Method for Efficient Deep Model Inference.pdf
2019 AutoPrune:Automatic Network Pruning by Regularing Auxiliary Parameters.pdf
2019 Efficient structured pruning and architecture searching for group convolution.pdf
2019 HAQ:Hardware-Aware Automated Quantization with Mixed Precision.pdf
2019 Meta filter pruning to accelerate deep convolutional neural networks.pdf
2019 Metapruning:Meta learning for automatic neural network channel pruning.pdf
2019 TAS:Network Pruning via Transformable Architecture Search.pdf
2020 ABCPruner:Channel Pruning via Automatic Structure Search.pdf
2020 APQ:Joint Search for Network Architecture, Pruning and Quantization Policy.pdf
2020 AutoCompress:An automatic DNN structured pruning framework for ultra-high compression rates.pdf
2020 AutoGAN-Distiller:Searching to Compress Generative Adversarial Network.pdf
2020 Automatic Neural Network Compression by Sparsity-Quantization Joint Learning:A Constrained Optimization-based Approach.pdf
2020 Automatic Pruning for Quantized Neural Networks.pdf
2020 AutoML for Architecting Efficient and Specialized Neural Networks.pdf
2020 DAIS:Automatic Channel Pruning via Differentiable Annealing Indicator Search.pdf
2020 DMCP:Differentiable Markov Channel Pruning for Neural Networks.pdf
2020 Learning Filter Pruning Criteriafor Deep Convolutional Neural Networks Acceleration.pdf
2020 SS-Auto:A Single-Shot, Automatic Structured Weight Pruning Framework of DNNs with Ultra-High Efficiency.pdf
2020 Towards Efficient Model Compression via Learned Global Ranking.pdf
2021 AACP:Model Compression by Accurate and Automatic Channel Pruning.pdf
2021 ABCP:Automatic Block-wise and Channel-wise Network Pruning via Joint Search.pdf
2021 ACP:Automatic Channel Pruning via Clustering ans Swarm Intelligence Optimization for CNN.pdf
2021 AdaBERT:Task-Adaptive BERT Compression with Differentiable Neural Architecture Search.pdf
2021 An Information Theory-inspired Strategy for Automatic Network Pruning.pdf
2021 Auto-prune:Automated DNN Pruning and Mapping for ReRAM-Based Accelerator.pdf
2021 AutoKD:Automatic Knowledge Distillation into A Student Architecture Family.pdf
2021 AutoLR:Layer-wise Pruning and Auto-tuning of Learning Rates in Fine-tuning of Deep Networks.pdf
2021 Automated Model Compression by Jointly Applied Pruning and Quantization.pdf
2021 Automatic Channel Pruning with Hyper-parameter Search and Dynamic Masking.pdf
2021 Boosting the Convergence of Reinforcement Learning-based Auto-pruning Using Historical Data.pdf
2021 CACP:Conditional Automated Channel Pruning for Deep Neural Networks.pdf
2021 CACP:Conditional Automated Channel Pruning for Deep Neural Networks(全).pdf
2021 Joint  Channel and  Weight  Pruning for  Model Acceleration on Mobile Devices.pdf
2021 Network Automatic Pruning:Start NAP and Take a Nap.pdf
2021 Pocketflow:An automated framework for compressing and accelerating Deep Neural Networks.pdf
2021 SuperPruner:Automatic Neural Network Pruning via Super Network.pdf
2021 Where to Prune:Using LSTM to Guide Data-Dependent Soft Pruning.pdf

About

This repo is a survey for: Neural Architecture Search & Auto Model Compress