Papers with Code 아카이브

Quantization

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법 전체 데이터셋

하위 태스크: 2
평가표: 10
보존된 평가 기록: 32

Quantization is a promising technique to reduce the computation cost of neural network training, which can replace high-cost floating-point numbers (e.g., float32) with low-cost fixed-point numbers (e.g., int8/int16).

Source: Adaptive Precision Training: Quantify Back Propagation in Neural Networks with Fixed-point Numbers

코드

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

https://github.com/StonyBrookNLP/HAQAE

공식 코드

Hierarchical Quantized Representations for Script Generation

https://github.com/SyphonArch/flash1dkmeans

공식 코드

Log-Time K-Means Clustering for 1D Data: Novel Approaches with Proof and Implementation

https://github.com/TAMU-VITA/GAN-Slimming

공식 코드

GAN Slimming: All-in-One GAN Compression by A Unified Optimization Framework

https://github.com/TUDB-Labs/MixLoRA

공식 코드

MixLoRA: Enhancing Large Language Models Fine-Tuning with LoRA-based Mixture of Experts

https://github.com/TaraEsmaeilbeig/one_bit_DoA_estimation

공식 코드

Deep Learning-Enabled One-Bit DoA Estimation

https://github.com/TencentYoutuResearch/CrowdCounting-SASNet

공식 코드

Uniformity in Heterogeneity:Diving Deep into Count Interval Partition for Crowd Counting

https://github.com/TheOpenSI/imu2pose-sionna

공식 코드

End-to-End Human Pose Reconstruction from Wearable Sensors for 6G Extended Reality Systems

https://github.com/Tiiiger/QPyTorch

공식 코드

QPyTorch: A Low-Precision Arithmetic Simulation Framework

https://github.com/Torment123/DFS

공식 코드

Fractional Skipping: Towards Finer-Grained Dynamic CNN Inference

https://github.com/UCMerced-ML/LC-model-compression

공식 코드

Model compression as constrained optimization, with application to neural nets. Part II: quantization

https://github.com/UMich-BipedLab/extrinsic_lidar_camera_calibration

공식 코드

Improvements to Target-Based 3D LiDAR to Camera Calibration

https://github.com/UMich-BipedLab/global_pose_estimation_for_optimal_shape

공식 코드

Optimal Target Shape for LiDAR Pose Estimation

https://github.com/USTC-IMCL/Task-driven-Semantic-Coding-via-RL

공식 코드

Task-driven Semantic Coding via Reinforcement Learning

https://github.com/USTC-JialunPeng/Diverse-Structure-Inpainting

공식 코드

Generating Diverse Structure for Image Inpainting With Hierarchical VQ-VAE

https://github.com/UniHD-CEG/arm-peak

공식 코드

Understanding Cache Boundness of ML Operators on ARM Processors

https://github.com/VDIGPKU/QGCN

공식 코드

Learning a Single Model with a Wide Range of Quality Factors for JPEG Image Artifacts Removal

https://github.com/VITA-Group/LightGaussian

공식 코드

LightGaussian: Unbounded 3D Gaussian Compression with 15x Reduction and 200+ FPS

https://github.com/VITA-Group/Q-GaLore

공식 코드

Q-GaLore: Quantized GaLore with INT4 Projection and Layer-Adaptive Low-Rank Gradients

https://github.com/VectorDB-NTU/Extended-RaBitQ

공식 코드

Practical and Asymptotically Optimal Quantization of High-Dimensional Vectors in Euclidean Space for Approximate Nearest Neighbor Search

https://github.com/VeritasXu/Ternary-Federated

공식 코드

Ternary Compression for Communication-Efficient Federated Learning

https://github.com/Victorletzelter/VoronoiWTA

공식 코드

Winner-takes-all learners are geometry-aware conditional density estimators

https://github.com/WeiHao97/DIVA

공식 코드

A Tale of Two Models: Constructing Evasive Attacks on Edge Models

https://github.com/Weiyu-USTC/CSGD

공식 코드

Communication-Censored Distributed Stochastic Gradient Descent

https://github.com/WeizhiGao/MoDiff

공식 코드

Modulated Diffusion: Accelerating Generative Modeling with Modulated Quantization

https://github.com/Wendison/VQMIVC

공식 코드

VQMIVC: Vector Quantization and Mutual Information-Based Unsupervised Speech Representation Disentanglement for One-shot Voice Conversion

https://github.com/Wenhui-Yu/LCFN

공식 코드

Graph Convolutional Network for Recommendation with Low-pass Collaborative Filters

https://github.com/Wi-sc/NVF

공식 코드

Neural Vector Fields: Implicit Representation by Explicit Learning

https://github.com/WillysMa/Digital_and_hybrid_precoding_design

공식 코드

Digital and Hybrid Precoding Designs in Massive MIMO with Low-Resolution ADCs

https://github.com/Windere/snn-cvt-dual-phase

공식 코드

Towards Lossless ANN-SNN Conversion under Ultra-Low Latency with Dual-Phase Optimization

https://github.com/XiaoFuLab/federated_max_var_gcca

공식 코드

Communication-Efficient Federated Linear and Deep Generalized Canonical Correlation Analysis

https://github.com/Xiaoxuan-Yang/HERO

공식 코드

HERO: Hessian-Enhanced Robust Optimization for Unifying and Improving Generalization and Quantization Performance

https://github.com/Xilinx/LSTM-PYNQ

공식 코드

FINN-L: Library Extensions and Design Trade-off Analysis for Variable Precision LSTM Networks on FPGAs

https://github.com/Xilinx/graffitist

공식 코드

Trained Quantization Thresholds for Accurate and Efficient Fixed-Point Inference of Deep Neural Networks

https://github.com/Xiuyu-Li/q-diffusion

공식 코드

Q-Diffusion: Quantizing Diffusion Models

https://github.com/YangNaruto/FQ-GAN

공식 코드

Feature Quantization Improves GAN Training

https://github.com/YangZhou08/Deep_Quantized_Recommendation_Model_DQRM

공식 코드

DQRM: Deep Quantized Recommendation Models

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