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/seolabcornell/torch2chip

공식 코드

Torch2Chip: An End-to-end Customizable Deep Neural Network Compression and Deployment Toolkit for Prototype Hardware Accelerator Design

https://github.com/seulkiyeom/LRP_Pruning_toy_example

공식 코드

Pruning by Explaining: A Novel Criterion for Deep Neural Network Pruning

https://github.com/seyoungahn/JSAC_FedDif

공식 코드

Communication-Efficient Diffusion Strategy for Performance Improvement of Federated Learning with Non-IID Data

https://github.com/seyoungahn/feddif

공식 코드

Communication-Efficient Diffusion Strategy for Performance Improvement of Federated Learning with Non-IID Data

https://github.com/shaiqmalik/Teacher-Class

공식 코드

Teacher-Class Network: A Neural Network Compression Mechanism

https://github.com/shaojiawei07/Edge_Inference_three-step_framework

공식 코드

Communication-Computation Trade-Off in Resource-Constrained Edge Inference

https://github.com/sharath-girish/lilnetx

공식 코드

LilNetX: Lightweight Networks with EXtreme Model Compression and Structured Sparsification

https://github.com/shawnricecake/search-llm

공식 코드

Search for Efficient Large Language Models

https://github.com/shi-labs/disparse-multitask-model-compression

공식 코드

DiSparse: Disentangled Sparsification for Multitask Model Compression

https://github.com/shihewang/fima-q

공식 코드

FIMA-Q: Post-Training Quantization for Vision Transformers by Fisher Information Matrix Approximation

https://github.com/shihuihong214/trio-vit

공식 코드

Trio-ViT: Post-Training Quantization and Acceleration for Softmax-Free Efficient Vision Transformer

https://github.com/shupenggui/ATMC

공식 코드

Model Compression with Adversarial Robustness: A Unified Optimization Framework

https://github.com/sidak/otfusion

공식 코드

Model Fusion via Optimal Transport

https://github.com/snudm-starlab/k-prune

공식 코드

Accurate Retraining-free Pruning for Pretrained Encoder-based Language Models

https://github.com/songmzhang/nmt-kd

공식 코드

Towards Understanding and Improving Knowledge Distillation for Neural Machine Translation

https://github.com/stanleybak/quantized_nn_backreach

공식 코드

Neural Network Compression of ACAS Xu Early Prototype is Unsafe: Closed-Loop Verification through Quantized State Backreachability

https://github.com/steve-zeyu-zhang/MedDet

공식 코드

MedDet: Generative Adversarial Distillation for Efficient Cervical Disc Herniation Detection

https://github.com/stiphyjay/lidar-ptq

공식 코드

LiDAR-PTQ: Post-Training Quantization for Point Cloud 3D Object Detection

https://github.com/sumansamui/small-footprint-keyword-spotting

공식 코드

Advances in Small-Footprint Keyword Spotting: A Comprehensive Review of Efficient Models and Algorithms

https://github.com/swapnildreams100/attacking_compressed_vits

공식 코드

Attacking Compressed Vision Transformers

https://github.com/swlzq/Semi-Online-KD

공식 코드

Semi-Online Knowledge Distillation

https://github.com/szcompressor/DeepSZ

공식 코드

DeepSZ: A Novel Framework to Compress Deep Neural Networks by Using Error-Bounded Lossy Compression

https://github.com/taehokim20/cprune

공식 코드

CPrune: Compiler-Informed Model Pruning for Efficient Target-Aware DNN Execution

https://github.com/tallamjr/astronet

공식 코드

The Tiny Time-series Transformer: Low-latency High-throughput Classification of Astronomical Transients using Deep Model Compression

https://github.com/tanmingkui/multiwaybp

공식 코드

The Shallow End: Empowering Shallower Deep-Convolutional Networks through Auxiliary Outputs

https://github.com/tansq/std-net

공식 코드

STD-NET: Search of Image Steganalytic Deep-learning Architecture via Hierarchical Tensor Decomposition

https://github.com/tebmer/awesome-knowledge-distillation-of-llms

공식 코드

A Survey on Knowledge Distillation of Large Language Models

https://github.com/terra-quantum-public/tqcompressedgpt2

공식 코드

TQCompressor: improving tensor decomposition methods in neural networks via permutations

https://github.com/tfjgeorge/ntk_alignment

공식 코드

Implicit Regularization via Neural Feature Alignment

https://github.com/thinklab-sjtu/twns

공식 코드

Ternary Weight Networks

https://github.com/thu-mig/pyra

공식 코드

PYRA: Parallel Yielding Re-Activation for Training-Inference Efficient Task Adaptation

https://github.com/thu-nics/moa

공식 코드

MoA: Mixture of Sparse Attention for Automatic Large Language Model Compression

https://github.com/thunlp/ca-lora

공식 코드

CA-LoRA: Adapting Existing LoRA for Compressed LLMs to Enable Efficient Multi-Tasking on Personal Devices

https://github.com/tianyic/obproxsg

공식 코드

Orthant Based Proximal Stochastic Gradient Method for $\ell_1$-Regularized Optimization

https://github.com/tianyic/only_train_once

공식 코드

OTOV2: Automatic, Generic, User-Friendly

https://github.com/timlee0212/PENNI

공식 코드

PENNI: Pruned Kernel Sharing for Efficient CNN Inference

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