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/rohanshenoy/qkeras
https://github.com/romik9999/fasttext-1925f09ed3
https://github.com/ruiqi-zhong/acl2021-instance-level
https://github.com/ruohaoguo/avis
TokenFlow: Unified Image Tokenizer for Multimodal Understanding and Generation
https://github.com/sahiltyagi4/gravac
Accordion: Adaptive Gradient Communication via Critical Learning Regime Identification
https://github.com/saintslab/pepr
https://github.com/sandai-org/magiattention
FlashAttention-3: Fast and Accurate Attention with Asynchrony and Low-precision
https://github.com/sanderwood/clamp3
MERT: Acoustic Music Understanding Model with Large-Scale Self-supervised Training
https://github.com/saqibjaved1/TC3DGS
Temporally Compressed 3D Gaussian Splatting for Dynamic Scenes
https://github.com/scottjiao/Gradient-Compression-Methods
QSGD: Communication-Efficient SGD via Gradient Quantization and Encoding
https://github.com/seulkiyeom/once-for-all
HAQ: Hardware-Aware Automated Quantization with Mixed Precision
https://github.com/sh-lee-prml/hierspeechpp
wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations
https://github.com/shaguopohuaizhe/TSAA
https://github.com/shayantalaei/quafl
QSGD: Communication-Efficient SGD via Gradient Quantization and Encoding
https://github.com/shivangi-aneja/FaceTalk
wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations
https://github.com/shiwendai/Faiss
https://github.com/shiyongming/calib-dataset-eval
Quantizing deep convolutional networks for efficient inference: A whitepaper
https://github.com/shizhouxing/Robustness-Verification-for-Transformers
Automatic Perturbation Analysis for Scalable Certified Robustness and Beyond
https://github.com/shrra/minisom
https://github.com/shuchiwu/rda
EMP-SSL: Towards Self-Supervised Learning in One Training Epoch
https://github.com/sithu31296/pose-estimation
SimCC: a Simple Coordinate Classification Perspective for Human Pose Estimation
https://github.com/smpanaro/ganq
GANQ: GPU-Adaptive Non-Uniform Quantization for Large Language Models
https://github.com/son-of-win/DeepDetectorDefense
Detecting Adversarial Image Examples in Deep Networks with Adaptive Noise Reduction
https://github.com/songhan/DSD
HAQ: Hardware-Aware Automated Quantization with Mixed Precision
https://github.com/songhan/Deep-Compression-AlexNet
https://github.com/songhan/SqueezeNet-Deep-Compression
https://github.com/songhan/SqueezeNet-Residual
HAQ: Hardware-Aware Automated Quantization with Mixed Precision
https://github.com/sony-si/ai-research/tree/master/HMQ
HMQ: Hardware Friendly Mixed Precision Quantization Block for CNNs
https://github.com/speechmatics/hqa
https://github.com/stanford-iliad/openvla-mini
https://github.com/stdacore/SinglePathOneShot_MAML
Single Path One-Shot Neural Architecture Search with Uniform Sampling
https://github.com/stevetsui/rbonn
https://github.com/stevetsui/rebnn
https://github.com/strawberryfg/c2f-3dhm-human-caffe
https://github.com/sung-yeon-kim/GENIUS-CVPR25
GENIUS: A Generative Framework for Universal Multimodal Search
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.