Papers with Code 아카이브
Quantization
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 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/IST-DASLab/QuEST
공식 코드QuEST: Stable Training of LLMs with 1-Bit Weights and Activations
https://github.com/Inpyo-Hong/AKT-Advanced-knowledge-Transfer
공식 코드https://github.com/IntelLabs/ScalableVectorSearch
공식 코드Similarity search in the blink of an eye with compressed indices
https://github.com/InterDigitalInc/CompressAI
공식 코드https://github.com/IvLabs/stagewise-knowledge-distillation
공식 코드https://github.com/JT-Ushio/MHA2MLA
공식 코드https://github.com/Jangho-Kim/PSG-pytorch
공식 코드Position-based Scaled Gradient for Model Quantization and Pruning
https://github.com/JasonSWFu/VQscore
공식 코드Self-Supervised Speech Quality Estimation and Enhancement Using Only Clean Speech
https://github.com/JimmySuen/integral-human-pose
공식 코드https://github.com/JingyangXiang/OvSW
공식 코드OvSW: Overcoming Silent Weights for Accurate Binary Neural Networks
https://github.com/JiwanSeo/RAQ-VAE
공식 코드https://github.com/Jundifang/PsyLite
공식 코드https://github.com/Jyonn/VQ4Rec
공식 코드Vector Quantization for Recommender Systems: A Review and Outlook
https://github.com/KUIS-AI-Tekalp-Research-Group/video-compression
공식 코드End-to-End Rate-Distortion Optimized Learned Hierarchical Bi-Directional Video Compression
https://github.com/KaidiXu/auto_LiRPA
공식 코드Automatic Perturbation Analysis for Scalable Certified Robustness and Beyond
https://github.com/KarenUllrich/Tutorial-SoftWeightSharingForNNCompression
공식 코드https://github.com/KeKsBoTer/c3dgs
공식 코드Compressed 3D Gaussian Splatting for Accelerated Novel View Synthesis
https://github.com/KokiKishimoto/cp_decomposition
공식 코드https://github.com/KokiKishimoto/cp_decomposition_alpha
공식 코드https://github.com/Kylin9511/ACRNet
공식 코드https://github.com/LMA-NeurIPS19/LMA
공식 코드https://github.com/LUOyk1999/NodeID
공식 코드Node Identifiers: Compact, Discrete Representations for Efficient Graph Learning
https://github.com/LaVieEnRoseSMZ/OQA
공식 코드Once Quantization-Aware Training: High Performance Extremely Low-bit Architecture Search
https://github.com/Lancer555/NICE
공식 코드NICE: Noise Injection and Clamping Estimation for Neural Network Quantization
https://github.com/LarsHoldijk/robust_LVQ_models
공식 코드Robustness of Generalized Learning Vector Quantization Models against Adversarial Attacks
https://github.com/Lucky-Lance/TerDiT
공식 코드https://github.com/MAGICS-LAB/GERM
공식 코드Fast and Low-Cost Genomic Foundation Models via Outlier Removal
https://github.com/MAGICS-LAB/GenoArmory
공식 코드GenoArmory: A Unified Evaluation Framework for Adversarial Attacks on Genomic Foundation Models
https://github.com/MHersche/HDembedding-BCI
공식 코드https://github.com/MICSim-official/MICSim_V1.0
공식 코드MICSim: A Modular Simulator for Mixed-signal Compute-in-Memory based AI Accelerator
https://github.com/MKJia/MGVQ
공식 코드MGVQ: Could VQ-VAE Beat VAE? A Generalizable Tokenizer with Multi-group Quantization
https://github.com/Menace-Dragon/VP-QOD
공식 코드https://github.com/Microsoft/LQ-Nets
공식 코드LQ-Nets: Learned Quantization for Highly Accurate and Compact Deep Neural Networks
https://github.com/Microsoft/LightGBM
공식 코드https://github.com/MihawkHu/DCASE2020_task1
공식 코드Device-Robust Acoustic Scene Classification Based on Two-Stage Categorization and Data Augmentation
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.