Papers with Code 아카이브
Neural Architecture Search
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 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/liamcli/gaea_release
공식 코드Geometry-Aware Gradient Algorithms for Neural Architecture Search
https://github.com/lightonai/contrastive-embeddings-for-neural-architectures
공식 코드https://github.com/linnanwang/AlphaX-NASBench101
공식 코드AlphaX: eXploring Neural Architectures with Deep Neural Networks and Monte Carlo Tree Search
https://github.com/linusericsson/einspace
공식 코드einspace: Searching for Neural Architectures from Fundamental Operations
https://github.com/liujiawei2333/cvpr2022-nas-competition-track-1-4th-solution
공식 코드Improve Ranking Correlation of Super-net through Training Scheme from One-shot NAS to Few-shot NAS
https://github.com/liuzhu-cv/crmef
공식 코드Searching a Compact Architecture for Robust Multi-Exposure Image Fusion
https://github.com/liuzhuang13/slimming
공식 코드Learning Efficient Convolutional Networks through Network Slimming
https://github.com/lixincn2015/Partial-Order-Pruning
공식 코드Partial Order Pruning: for Best Speed/Accuracy Trade-off in Neural Architecture Search
https://github.com/llnl/xnas
공식 코드Learning Interpretable Models Through Multi-Objective Neural Architecture Search
https://github.com/logue311/EDNAS
공식 코드Efficient Decoupled Neural Architecture Search by Structure and Operation Sampling
https://github.com/lolemacs/soft-sharing
공식 코드Learning Implicitly Recurrent CNNs Through Parameter Sharing
https://github.com/longkaifang/3d-adnas
공식 코드Revisiting Multimodal Fusion for 3D Anomaly Detection from an Architectural Perspective
https://github.com/lordzth666/-cvprw-csco
공식 코드https://github.com/lordzth666/WACV23_PIDS-Joint-Point-Interaction-Dimension-Search-for-3D-Point-Cloud
공식 코드PIDS: Joint Point Interaction-Dimension Search for 3D Point Cloud
https://github.com/lordzth666/WWW-23_NASRec
공식 코드NASRec: Weight Sharing Neural Architecture Search for Recommender Systems
https://github.com/lorenmt/shape-adaptor
공식 코드https://github.com/lr94/abas
공식 코드Adversarial Branch Architecture Search for Unsupervised Domain Adaptation
https://github.com/luffy06/refusion
공식 코드https://github.com/luke-mcdermott-mi/distilled-pruning
공식 코드https://github.com/luminxu/ViPNAS
공식 코드ViPNAS: Efficient Video Pose Estimation via Neural Architecture Search
https://github.com/lyq998/HAAP
공식 코드https://github.com/lzvv123456/sswp-nas
공식 코드Towards Self-supervised and Weight-preserving Neural Architecture Search
https://github.com/madoibito80/advantage-nas
공식 코드AdvantageNAS: Efficient Neural Architecture Search with Credit Assignment
https://github.com/maestro-project/gamma-timeloop
공식 코드https://github.com/mahdihosseini/CONetV2
공식 코드https://github.com/mahdihosseini/DARTS-ADP
공식 코드https://github.com/mahdihosseini/conet
공식 코드CONet: Channel Optimization for Convolutional Neural Networks
https://github.com/mahdihosseini/pibconv
공식 코드Pseudo-Inverted Bottleneck Convolution for DARTS Search Space
https://github.com/mahsapaknezhad/part
공식 코드https://github.com/marsggbo/CovidNet3D
공식 코드https://github.com/marsggbo/EAGAN
공식 코드EAGAN: Efficient Two-stage Evolutionary Architecture Search for GANs
https://github.com/marsggbo/automl_a_survey_of_state_of_the_art
공식 코드https://github.com/marsggbo/miccai2022-emars
공식 코드https://github.com/marsggbo/nas-lid
공식 코드NAS-LID: Efficient Neural Architecture Search with Local Intrinsic Dimension
https://github.com/matt-lourens/dynamic-qcnn
공식 코드Hierarchical quantum circuit representations for neural architecture search
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.