Papers with Code 아카이브

Neural Architecture Search

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법 전체 데이터셋

하위 태스크: 1
평가표: 26
보존된 평가 기록: 424

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

코드

관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.

https://github.com/diff7/QuanToaster

공식 코드

QuantNAS for super resolution: searching for efficient quantization-friendly architectures against quantization noise

https://github.com/dingmyu/HR-NAS

공식 코드

HR-NAS: Searching Efficient High-Resolution Neural Architectures with Lightweight Transformers

https://github.com/dingmyu/NCP

공식 코드

Learning Versatile Neural Architectures by Propagating Network Codes

https://github.com/dlongry/solution-to-cvpr2021-nas-track2

공식 코드

Cascade Bagging for Accuracy Prediction with Few Training Samples

https://github.com/dooleys/fr-nas

공식 코드

Rethinking Bias Mitigation: Fairer Architectures Make for Fairer Face Recognition

https://github.com/dotwang/hknas

공식 코드

HKNAS: Classification of Hyperspectral Imagery Based on Hyper Kernel Neural Architecture Search

https://github.com/dounialakhmiri/iclr_haet2021

공식 코드

Efficient Training Under Limited Resources

https://github.com/dr-faustus/lambda-darts

공식 코드

$Λ$-DARTS: Mitigating Performance Collapse by Harmonizing Operation Selection among Cells

https://github.com/drsleep/nas-segm-pytorch

공식 코드

Fast Neural Architecture Search of Compact Semantic Segmentation Models via Auxiliary Cells

https://github.com/dstamoulis/single-path-nas

공식 코드

Single-Path NAS: Designing Hardware-Efficient ConvNets in less than 4 Hours

https://github.com/duanyiqun/ctnas-eeg

공식 코드

Cross Task Neural Architecture Search for EEG Signal Classifications

https://github.com/egracheva/epsinas

공식 코드

Neural Architecture Search via Two Constant Shared Weights Initialisations

https://github.com/ehw-fit/nascaps

공식 코드

NASCaps: A Framework for Neural Architecture Search to Optimize the Accuracy and Hardware Efficiency of Convolutional Capsule Networks

https://github.com/ehw-fit/rohnas

공식 코드

RoHNAS: A Neural Architecture Search Framework with Conjoint Optimization for Adversarial Robustness and Hardware Efficiency of Convolutional and Capsule Networks

https://github.com/ejokhan/transnas_tsad

공식 코드

TransNAS-TSAD: Harnessing Transformers for Multi-Objective Neural Architecture Search in Time Series Anomaly Detection

https://github.com/ekhao/dataawareneuralarchitecturesearch

공식 코드

Data Aware Neural Architecture Search

https://github.com/eliberis/uNAS

공식 코드

$μ$NAS: Constrained Neural Architecture Search for Microcontrollers

https://github.com/elisabethjs/ectonas

공식 코드

ECToNAS: Evolutionary Cross-Topology Neural Architecture Search

https://github.com/embeddedml-edagroup/pit

공식 코드

Lightweight Neural Architecture Search for Temporal Convolutional Networks at the Edge

https://github.com/embeddedml-edagroup/q-ppg

공식 코드

Q-PPG: Energy-Efficient PPG-based Heart Rate Monitoring on Wearable Devices

https://github.com/emi-group/evoxbench

공식 코드

Neural Architecture Search as Multiobjective Optimization Benchmarks: Problem Formulation and Performance Assessment

https://github.com/emi-group/fr-nas

공식 코드

FR-NAS: Forward-and-Reverse Graph Predictor for Efficient Neural Architecture Search

https://github.com/eml-eda/multi-constraint-nas

공식 코드

Enhancing Neural Architecture Search with Multiple Hardware Constraints for Deep Learning Model Deployment on Tiny IoT Devices

https://github.com/eml-eda/multi-prec-nas

공식 코드

Channel-wise Mixed-precision Assignment for DNN Inference on Constrained Edge Nodes

https://github.com/eml-eda/plinio

공식 코드

Enhancing Neural Architecture Search with Multiple Hardware Constraints for Deep Learning Model Deployment on Tiny IoT Devices

https://github.com/emory-melody/graphslim

공식 코드

GC4NC: A Benchmark Framework for Graph Condensation on Node Classification with New Insights

https://github.com/ernie1/pi-nas

공식 코드

Pi-NAS: Improving Neural Architecture Search by Reducing Supernet Training Consistency Shift

https://github.com/ethanygao/aux-nas

공식 코드

Aux-NAS: Exploiting Auxiliary Labels with Negligibly Extra Inference Cost

https://github.com/euphoria16/shapley-nas

공식 코드

Shapley-NAS: Discovering Operation Contribution for Neural Architecture Search

https://github.com/eurecom-asp/pc-darts-anti-spoofing

공식 코드

Partially-Connected Differentiable Architecture Search for Deepfake and Spoofing Detection

https://github.com/eustomaqua/SAEP

공식 코드

Sub-Architecture Ensemble Pruning in Neural Architecture Search

https://github.com/facebookresearch/AlphaNet

공식 코드

AlphaNet: Improved Training of Supernets with Alpha-Divergence

https://github.com/facebookresearch/AttentiveNAS

공식 코드

AttentiveNAS: Improving Neural Architecture Search via Attentive Sampling

https://github.com/facebookresearch/LaMCTS

공식 코드

Sample-Efficient Neural Architecture Search by Learning Action Space

https://github.com/facebookresearch/mobile-vision

공식 코드

FBNet: Hardware-Aware Efficient ConvNet Design via Differentiable Neural Architecture Search

https://github.com/facebookresearch/nasrec

공식 코드

NASRec: Weight Sharing Neural Architecture Search for Recommender Systems

출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.