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/vdigpku/nas-bnn

공식 코드

NAS-BNN: Neural Architecture Search for Binary Neural Networks

https://github.com/vidhur2k/CS8803-Project

공식 코드

Efficient Incorporation of Multiple Latency Targets in the Once-For-All Network

https://github.com/viharoszsolt/idenas

공식 코드

Model Input-Output Configuration Search with Embedded Feature Selection for Sensor Time-series and Image Classification

https://github.com/vimar-gu/msinet

공식 코드

MSINet: Twins Contrastive Search of Multi-Scale Interaction for Object ReID

https://github.com/vita-group/architecture_convergence

공식 코드

Deep Architecture Connectivity Matters for Its Convergence: A Fine-Grained Analysis

https://github.com/vita-group/tegnas

공식 코드

Understanding and Accelerating Neural Architecture Search with Training-Free and Theory-Grounded Metrics

https://github.com/vovantuan1999a/OoD-ViT-NAS

공식 코드

Vision Transformer Neural Architecture Search for Out-of-Distribution Generalization: Benchmark and Insights

https://github.com/walkerning/aw_nas

공식 코드

A Generic Graph-based Neural Architecture Encoding Scheme for Predictor-based NAS

https://github.com/walkerning/aw_nas/tree/master/examples/research/ftt-nas

공식 코드

FTT-NAS: Discovering Fault-Tolerant Convolutional Neural Architecture

https://github.com/wentaozhu/AutoShot

공식 코드

AutoShot: A Short Video Dataset and State-of-the-Art Shot Boundary Detection

https://github.com/wentaozhu/speechnas

공식 코드

SpeechNAS: Towards Better Trade-off between Latency and Accuracy for Large-Scale Speaker Verification

https://github.com/wenwei202/autogrow

공식 코드

AutoGrow: Automatic Layer Growing in Deep Convolutional Networks

https://github.com/whittle-org/plm_pruning

공식 코드

Structural Pruning of Pre-trained Language Models via Neural Architecture Search

https://github.com/wiljohnhong/dropnas

공식 코드

DropNAS: Grouped Operation Dropout for Differentiable Architecture Search

https://github.com/wmcnally/evopose2d

공식 코드

EvoPose2D: Pushing the Boundaries of 2D Human Pose Estimation using Accelerated Neuroevolution with Weight Transfer

https://github.com/woodywff/nas_3d_unet

공식 코드

Neural Architecture Search for Gliomas Segmentation on Multimodal Magnetic Resonance Imaging

https://github.com/wufan-cse/g-nas

공식 코드

G-NAS: Generalizable Neural Architecture Search for Single Domain Generalization Object Detection

https://github.com/wuxingyu-ai/llm4ec

공식 코드

Evolutionary Computation in the Era of Large Language Model: Survey and Roadmap

https://github.com/wuyushuwys/compiler-aware-nas-sr

공식 코드

Compiler-Aware Neural Architecture Search for On-Mobile Real-time Super-Resolution

https://github.com/wyjeong/tans

공식 코드

Task-Adaptive Neural Network Search with Meta-Contrastive Learning

https://github.com/xiandaguo/sposgait

공식 코드

Gait Recognition in the Wild: A Large-scale Benchmark and NAS-based Baseline

https://github.com/xiangning-chen/DrNAS

공식 코드

DrNAS: Dirichlet Neural Architecture Search

https://github.com/xiangning-chen/SmoothDARTS

공식 코드

Stabilizing Differentiable Architecture Search via Perturbation-based Regularization

https://github.com/xiaofangxd/KEGNAS

공식 코드

Knowledge-aware Evolutionary Graph Neural Architecture Search

https://github.com/xiaomi-automl/MixPath

공식 코드

MixPath: A Unified Approach for One-shot Neural Architecture Search

https://github.com/xiaomi-automl/MoGA

공식 코드

MoGA: Searching Beyond MobileNetV3

https://github.com/xiaomi-automl/NoisyDARTS

공식 코드

Noisy Differentiable Architecture Search

https://github.com/xiaomi-automl/SCARLET-NAS

공식 코드

SCARLET-NAS: Bridging the Gap between Stability and Scalability in Weight-sharing Neural Architecture Search

https://github.com/xiaomi-automl/fairdarts

공식 코드

Fair DARTS: Eliminating Unfair Advantages in Differentiable Architecture Search

https://github.com/xingchenwan/cell-based-nas-analysis

공식 코드

On Redundancy and Diversity in Cell-based Neural Architecture Search

https://github.com/xiusu/NAS-Bench-Macro

공식 코드

Prioritized Architecture Sampling with Monto-Carlo Tree Search

https://github.com/xiusu/ViTAS

공식 코드

ViTAS: Vision Transformer Architecture Search

https://github.com/xujinfan/NASP-codes

공식 코드

Efficient Neural Architecture Search via Proximal Iterations

https://github.com/yanghr/BSQ

공식 코드

BSQ: Exploring Bit-Level Sparsity for Mixed-Precision Neural Network Quantization

https://github.com/yangsenius/PoseNFS

공식 코드

Pose Neural Fabrics Search

https://github.com/yaya-yns/tart

공식 코드

TART: Token-based Architecture Transformer for Neural Network Performance Prediction

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