Papers with Code 아카이브

Model Compression

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법 전체 데이터셋

하위 태스크: 1
평가표: 2
보존된 평가 기록: 14

Model Compression is an actively pursued area of research over the last few years with the goal of deploying state-of-the-art deep networks in low-power and resource limited devices without significant drop in accuracy. Parameter pruning, low-rank factorization and weight quantization are some of the proposed methods to compress the size of deep networks.

Source: KD-MRI: A knowledge distillation framework for image reconstruction and image restoration in MRI workflow

코드

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

https://bitbucket.org/YanivShu/binary_weighted_networks_public

공식 코드

Exact Backpropagation in Binary Weighted Networks with Group Weight Transformations

https://github.com/1adrianb/binary-networks-pytorch

공식 코드

XNOR-Net++: Improved Binary Neural Networks

https://github.com/1e12Leon/RemoteTrimmer

공식 코드

RemoteTrimmer: Adaptive Structural Pruning for Remote Sensing Image Classification

https://github.com/1hunters/retraining-free-quantization

공식 코드

Retraining-free Model Quantization via One-Shot Weight-Coupling Learning

https://github.com/42shawn/causal-dfq

공식 코드

Causal-DFQ: Causality Guided Data-free Network Quantization

https://github.com/594422814/CF-VGG

공식 코드

Real-Time Correlation Tracking via Joint Model Compression and Transfer

https://github.com/Accenture/Labs-Federated-Learning

공식 코드

Clustered Sampling: Low-Variance and Improved Representativity for Clients Selection in Federated Learning

https://github.com/BGUCompSci/WaveletCompressedConvolution

공식 코드

Wavelet Feature Maps Compression for Image-to-Image CNNs

https://github.com/Bala93/KD-MRI

공식 코드

KD-MRI: A knowledge distillation framework for image reconstruction and image restoration in MRI workflow

https://github.com/BayesWatch/pytorch-prunes

공식 코드

A Closer Look at Structured Pruning for Neural Network Compression

https://github.com/BerivanIsik/SuRP

공식 코드

An Information-Theoretic Justification for Model Pruning

https://github.com/BoseCorp/efficient-neural-speech-enhancement

공식 코드

TinyLSTMs: Efficient Neural Speech Enhancement for Hearing Aids

https://github.com/ByungKwanLee/Masking-Adversarial-Damage

공식 코드

Masking Adversarial Damage: Finding Adversarial Saliency for Robust and Sparse Network

https://github.com/ChaofanTao/FAT_Quantization

공식 코드

FAT: Learning Low-Bitwidth Parametric Representation via Frequency-Aware Transformation

https://github.com/ChristopherSweeney/SlimNets

공식 코드

SlimNets: An Exploration of Deep Model Compression and Acceleration

https://github.com/DT42/squeezenet_demo

공식 코드

SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size

https://github.com/DeepScale/SqueezeNet

공식 코드

SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size

https://github.com/DingXiaoH/GSM-SGD

공식 코드

Global Sparse Momentum SGD for Pruning Very Deep Neural Networks

https://github.com/Element-Research/dpnn

공식 코드

SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size

https://github.com/FLHonker/Awesome-Knowledge-Distillation

공식 코드

Knowledge Distillation and Student-Teacher Learning for Visual Intelligence: A Review and New Outlooks

https://github.com/FederatedML/FedCompress

공식 코드

Communication-Efficient Federated Learning through Adaptive Weight Clustering and Server-Side Distillation

https://github.com/GongCheng1919/VecQ

공식 코드

VecQ: Minimal Loss DNN Model Compression With Vectorized Weight Quantization

https://github.com/HelloZicky/DUET

공식 코드

DUET: A Tuning-Free Device-Cloud Collaborative Parameters Generation Framework for Efficient Device Model Generalization

https://github.com/HobbitLong/RepDistiller

공식 코드

Contrastive Representation Distillation

https://github.com/Hyeji-Kim/ENC

공식 코드

Efficient Neural Network Compression

https://github.com/IST-DASLab/DarwinLM

공식 코드

DarwinLM: Evolutionary Structured Pruning of Large Language Models

https://github.com/IST-DASLab/WoodFisher

공식 코드

WoodFisher: Efficient Second-Order Approximation for Neural Network Compression

https://github.com/IU-SAIGE/contrastive_mixtures

공식 코드

Self-Supervised Learning from Contrastive Mixtures for Personalized Speech Enhancement

https://github.com/Isnot2bad/Micro-Net

공식 코드

A Miniaturized Semantic Segmentation Method for Remote Sensing Image

https://github.com/IvLabs/stagewise-knowledge-distillation

공식 코드

Data Efficient Stagewise Knowledge Distillation

https://github.com/Jangho-Kim/Factor-Transfer-pytorch

공식 코드

Paraphrasing Complex Network: Network Compression via Factor Transfer

https://github.com/Jangho-Kim/PSG-pytorch

공식 코드

Position-based Scaled Gradient for Model Quantization and Pruning

https://github.com/JetRunner/BERT-of-Theseus

공식 코드

BERT-of-Theseus: Compressing BERT by Progressive Module Replacing

https://github.com/JiaxiLi1/OWLed

공식 코드

OWLed: Outlier-weighed Layerwise Pruning for Efficient Autonomous Driving Framework

https://github.com/KaiqiZhang/ADAM-ADMM

공식 코드

StructADMM: A Systematic, High-Efficiency Framework of Structured Weight Pruning for DNNs

https://github.com/KarenUllrich/Tutorial-SoftWeightSharingForNNCompression

공식 코드

Soft Weight-Sharing for Neural Network Compression

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