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://github.com/openvinotoolkit/nncf

공식 코드

Neural Network Compression Framework for fast model inference

https://github.com/openvinotoolkit/nncf_pytorch

공식 코드

Neural Network Compression Framework for fast model inference

https://github.com/ososos888/prune-then-distill

공식 코드

Prune Your Model Before Distill It

https://github.com/pavanteja295/CACL

공식 코드

Compression-aware Continual Learning using Singular Value Decomposition

https://github.com/peiyanflying/spvit

공식 코드

SPViT: Enabling Faster Vision Transformers via Soft Token Pruning

https://github.com/pfnet-research/einconv

공식 코드

Einconv: Exploring Unexplored Tensor Network Decompositions for Convolutional Neural Networks

https://github.com/philipco/mcm-bidirectional-compression

공식 코드

Preserved central model for faster bidirectional compression in distributed settings

https://github.com/pixeli99/mixln

공식 코드

Mix-LN: Unleashing the Power of Deeper Layers by Combining Pre-LN and Post-LN

https://github.com/pppa2019/contexualdynamicmapping

공식 코드

Enhancing Cross-Tokenizer Knowledge Distillation with Contextual Dynamical Mapping

https://github.com/princeton-nlp/cofipruning

공식 코드

Structured Pruning Learns Compact and Accurate Models

https://github.com/priyankkalgaonkar/Image-Classification-with-CondenseNeXt-for-ARM-Based-Computing-Platforms

공식 코드

Image Classification with CondenseNeXt for ARM-Based Computing Platforms

https://github.com/pty72/rlkd

공식 코드

Enhancing Knowledge Distillation of Large Language Models through Efficient Multi-Modal Distribution Alignment

https://github.com/purdue-nrl/Gradual-Channel-Pruning-using-FRS

공식 코드

Gradual Channel Pruning while Training using Feature Relevance Scores for Convolutional Neural Networks

https://github.com/pytorch/fairseq

공식 코드

Training with Quantization Noise for Extreme Model Compression

https://github.com/qigongsun/BMD

공식 코드

Quantized Neural Networks via {-1, +1} Encoding Decomposition and Acceleration

https://github.com/rafael-a-monteiro-math/Binary_classification_phase_separation

공식 코드

Binary Classification as a Phase Separation Process

https://github.com/rahimentezari/Sensys-ml2020

공식 코드

Class-dependent Compression of Deep Neural Networks

https://github.com/razvandu/dynamicslicing

공식 코드

Change Is the Only Constant: Dynamic LLM Slicing based on Layer Redundancy

https://github.com/reddragon/efficient-dl-survey-paper

공식 코드

Efficient Deep Learning: A Survey on Making Deep Learning Models Smaller, Faster, and Better

https://github.com/rohitrai11/application-specific-compression-of-deep-learning-models

공식 코드

Application Specific Compression of Deep Learning Models

https://github.com/roryshao/dfkd-fgvc

공식 코드

Data-free Knowledge Distillation for Fine-grained Visual Categorization

https://github.com/rossqin/RQNet

공식 코드

A Real-time Low-cost Artificial Intelligence System for Autonomous Spraying in Palm Plantations

https://github.com/rotmanguy/amoc

공식 코드

Model Compression for Domain Adaptation through Causal Effect Estimation

https://github.com/ruckbreasoning/llm-streamline

공식 코드

Streamlining Redundant Layers to Compress Large Language Models

https://github.com/ruiyangju/threshnet

공식 코드

ThreshNet: An Efficient DenseNet Using Threshold Mechanism to Reduce Connections

https://github.com/runpeidong/pointdistiller

공식 코드

PointDistiller: Structured Knowledge Distillation Towards Efficient and Compact 3D Detection

https://github.com/ryan-prime/3dg-stfm

공식 코드

3DG-STFM: 3D Geometric Guided Student-Teacher Feature Matching

https://github.com/saintslab/adver-fine

공식 코드

Adversarial Fine-tuning of Compressed Neural Networks for Joint Improvement of Robustness and Efficiency

https://github.com/samaonline/Recurrent-Parameter-Generators

공식 코드

Compact and Optimal Deep Learning with Recurrent Parameter Generators

https://github.com/sands-lab/layer-wise-aaai20

공식 코드

On the Discrepancy between the Theoretical Analysis and Practical Implementations of Compressed Communication for Distributed Deep Learning

https://github.com/sanglee/caffe-mc-opencl

공식 코드

Compressed Learning of Deep Neural Networks for OpenCL-Capable Embedded Systems

https://github.com/saqibjaved1/QT-DoG

공식 코드

QT-DoG: Quantization-aware Training for Domain Generalization

https://github.com/sarababakn/flash_fl

공식 코드

Lottery Aware Sparsity Hunting: Enabling Federated Learning on Resource-Limited Edge

https://github.com/sbwww/cost-eff

공식 코드

COST-EFF: Collaborative Optimization of Spatial and Temporal Efficiency with Slenderized Multi-exit Language Models

https://github.com/sdc17/upop

공식 코드

UPop: Unified and Progressive Pruning for Compressing Vision-Language Transformers

https://github.com/sempraety/pruning-via-merging

공식 코드

Pruning via Merging: Compressing LLMs via Manifold Alignment Based Layer Merging

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