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/changlin31/DS-Net

공식 코드

Dynamic Slimmable Network

https://github.com/chen123ctrls/enhancingicl_svdpruning

공식 코드

Enhancing In-Context Learning Performance with just SVD-Based Weight Pruning: A Theoretical Perspective

https://github.com/cheneydon/hrkd

공식 코드

HRKD: Hierarchical Relational Knowledge Distillation for Cross-domain Language Model Compression

https://github.com/chengang95/unkd

공식 코드

Unbiased Knowledge Distillation for Recommendation

https://github.com/chenjallen/resource-constrained-compression-on-snn

공식 코드

Resource Constrained Model Compression via Minimax Optimization for Spiking Neural Networks

https://github.com/chensy7/efficient-vit

공식 코드

Compressing Vision Transformers for Low-Resource Visual Learning

https://github.com/chenyangli-97/nn-bcd

공식 코드

On Model Compression for Neural Networks: Framework, Algorithm, and Convergence Guarantee

https://github.com/christian-lyc/nam

공식 코드

NAM: Normalization-based Attention Module

https://github.com/chrundle/biprop

공식 코드

A Winning Hand: Compressing Deep Networks Can Improve Out-Of-Distribution Robustness

https://github.com/chumingqian/Model_Compression_For_YOLOV3-V4

공식 코드

Group channel pruning and spatial attention distilling for object detection

https://github.com/cityu-aim-group/gfbs

공식 코드

Exploring Gradient Flow Based Saliency for DNN Model Compression

https://github.com/cliang1453/super-structured-lottery-tickets

공식 코드

Super Tickets in Pre-Trained Language Models: From Model Compression to Improving Generalization

https://github.com/cliang1453/task-aware-distillation

공식 코드

Less is More: Task-aware Layer-wise Distillation for Language Model Compression

https://github.com/clovaai/attention-feature-distillation

공식 코드

Show, Attend and Distill:Knowledge Distillation via Attention-based Feature Matching

https://github.com/cmu-enyac/LeGR

공식 코드

Towards Efficient Model Compression via Learned Global Ranking

https://github.com/codestar12/Parallel-Independent-Blockwise-Distillation

공식 코드

Parallel Blockwise Knowledge Distillation for Deep Neural Network Compression

https://github.com/colehawkins/bayesian-tensor-rank-determination

공식 코드

Towards Compact Neural Networks via End-to-End Training: A Bayesian Tensor Approach with Automatic Rank Determination

https://github.com/copenlu/tx-ray

공식 코드

TX-Ray: Quantifying and Explaining Model-Knowledge Transfer in (Un-)Supervised NLP

https://github.com/cornell-zhang/dnn-quant-ocs

공식 코드

Improving Neural Network Quantization without Retraining using Outlier Channel Splitting

https://github.com/cranken/cpd

공식 코드

Comb, Prune, Distill: Towards Unified Pruning for Vision Model Compression

https://github.com/crystaleye42/eval-safety

공식 코드

Pruning for Protection: Increasing Jailbreak Resistance in Aligned LLMs Without Fine-Tuning

https://github.com/cscvlab/3D-Objects-Compression

공식 코드

High-fidelity 3D Model Compression based on Key Spheres

https://github.com/cunningham-lab/cb_and_cc

공식 코드

The continuous categorical: a novel simplex-valued exponential family

https://github.com/cvmi-lab/sparsekd

공식 코드

Towards Efficient 3D Object Detection with Knowledge Distillation

https://github.com/daixinghome/Distill_GID_detectron2

공식 코드

General Instance Distillation for Object Detection

https://github.com/daskol/fewbit

공식 코드

Memory-Efficient Backpropagation through Large Linear Layers

https://github.com/dayu11/selective_pretraining_for_private_finetuning

공식 코드

Selective Pre-training for Private Fine-tuning

https://github.com/deep-fry/mayo

공식 코드

Dynamic Channel Pruning: Feature Boosting and Suppression

https://github.com/dkozlov/awesome-knowledge-distillation

공식 코드

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

https://github.com/drsy/motis

공식 코드

Leaner and Faster: Two-Stage Model Compression for Lightweight Text-Image Retrieval

https://github.com/dsshim0125/gaussian-ram

공식 코드

Gaussian RAM: Lightweight Image Classification via Stochastic Retina-Inspired Glimpse and Reinforcement Learning

https://github.com/duguodong7/graftllm

공식 코드

Knowledge Grafting of Large Language Models

https://github.com/duzhixing/FRS

공식 코드

Distilling Object Detectors with Feature Richness

https://github.com/eclipsess/chip_neurips2021

공식 코드

CHIP: CHannel Independence-based Pruning for Compact Neural Networks

https://github.com/eduardacaldeira/compression_bias_survey

공식 코드

Model Compression Techniques in Biometrics Applications: A Survey

https://github.com/edwardmagongo/quantum-inspired-model-compression

공식 코드

QIANets: Quantum-Integrated Adaptive Networks for Reduced Latency and Improved Inference Times in CNN Models

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