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/shaochenze/ear
공식 코드Continuous Visual Autoregressive Generation via Score Maximization
https://github.com/shaoyuanlo/Halftoning-Defense
공식 코드https://github.com/sharc-lab/rapid-inr
공식 코드Rapid-INR: Storage Efficient CPU-free DNN Training Using Implicit Neural Representation
https://github.com/sharpiless/rgal
공식 코드Relation-Guided Adversarial Learning for Data-free Knowledge Transfer
https://github.com/shawnricecake/agile-quant
공식 코드Agile-Quant: Activation-Guided Quantization for Faster Inference of LLMs on the Edge
https://github.com/shawnricecake/edgeqat
공식 코드https://github.com/shawnricecake/quart-depth
공식 코드QuartDepth: Post-Training Quantization for Real-Time Depth Estimation on the Edge
https://github.com/shawnricecake/search-llm
공식 코드https://github.com/shigangli/magicube
공식 코드Efficient Quantized Sparse Matrix Operations on Tensor Cores
https://github.com/shihewang/fima-q
공식 코드https://github.com/shihuihong214/p2-vit
공식 코드https://github.com/shihuihong214/trio-vit
공식 코드Trio-ViT: Post-Training Quantization and Acceleration for Softmax-Free Efficient Vision Transformer
https://github.com/shivram1987/visiontransformerhashing
공식 코드https://github.com/shravanvn/cnqs
공식 코드Continuous-variable neural-network quantum states and the quantum rotor model
https://github.com/shuai-huang/1Bit-CS
공식 코드Approximate Message Passing with Parameter Estimation for Heavily Quantized Measurements
https://github.com/shubhamchandak94/LFZip
공식 코드LFZip: Lossy compression of multivariate floating-point time series data via improved prediction
https://github.com/shuimove1234/Noise-Invariant-Frame-Selection
공식 코드https://github.com/shunli-wang/ca-spacenet
공식 코드CA-SpaceNet: Counterfactual Analysis for 6D Pose Estimation in Space
https://github.com/shupenggui/ATMC
공식 코드Model Compression with Adversarial Robustness: A Unified Optimization Framework
https://github.com/sike-wang/low-bit-shampoo
공식 코드https://github.com/siyuhuang/quantart
공식 코드QuantArt: Quantizing Image Style Transfer Towards High Visual Fidelity
https://github.com/sjlmg/cp-kgc
공식 코드https://github.com/skhobahi/deep1bitVAE
공식 코드Model-Aware Deep Architectures for One-Bit Compressive Variational Autoencoding
https://github.com/smartcameras/RP-FGSM
공식 코드Exploiting vulnerabilities of deep neural networks for privacy protection
https://github.com/snap-research/f8net
공식 코드F8Net: Fixed-Point 8-bit Only Multiplication for Network Quantization
https://github.com/snap-research/graphless-neural-networks
공식 코드Graph-less Neural Networks: Teaching Old MLPs New Tricks via Distillation
https://github.com/snu-arc/any-precision-llm
공식 코드Any-Precision LLM: Low-Cost Deployment of Multiple, Different-Sized LLMs
https://github.com/snu-mllab/guidedquant
공식 코드GuidedQuant: Large Language Model Quantization via Exploiting End Loss Guidance
https://github.com/sony-si/ai-research
공식 코드HMQ: Hardware Friendly Mixed Precision Quantization Block for CNNs
https://github.com/sony/ai-research-code
공식 코드Mixed Precision DNNs: All you need is a good parametrization
https://github.com/sony/model_optimization
공식 코드https://github.com/sony/sqvae
공식 코드SQ-VAE: Variational Bayes on Discrete Representation with Self-annealed Stochastic Quantization
https://github.com/sotiraslab/SC-VAE
공식 코드SC-VAE: Sparse Coding-based Variational Autoencoder with Learned ISTA
https://github.com/spallanzanimatteo/QuantLab
공식 코드Additive Noise Annealing and Approximation Properties of Quantized Neural Networks
https://github.com/spcl/quarot
공식 코드출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.