PACT: Parameterized Clipping Activation for Quantized Neural Networks (original) (raw)

Accurate and Efficient 2-bit Quantized Neural Networks

Kailash Gopalakrishnan

2019

View PDFchevron_right

Low-bit Quantization of Neural Networks for Efficient Inference

Pavel Kisilev

2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW), 2019

View PDFchevron_right

Ultra-Low Precision 4-bit Training of Deep Neural Networks

Kaoutar El Maghraoui

2020

View PDFchevron_right

Bit Efficient Quantization for Deep Neural Networks

Sek Chai

2019 Fifth Workshop on Energy Efficient Machine Learning and Cognitive Computing - NeurIPS Edition (EMC2-NIPS), 2019

View PDFchevron_right

A White Paper on Neural Network Quantization

Marios Fournarakis

2021

View PDFchevron_right

ACIQ: Analytical Clipping for Integer Quantization of neural networks

Ron Banner

ArXiv, 2018

View PDFchevron_right

Incremental Network Quantization: Towards Lossless CNNs with Low-Precision Weights

Aojun Zhou

ArXiv, 2017

View PDFchevron_right

Dataflow-based Joint Quantization of Weights and Activations for Deep Neural Networks

joseph pal

ArXiv, 2019

View PDFchevron_right

A Novel Low-Bit Quantization Strategy for Compressing Deep Neural Networks

Dianle Zhou

Computational Intelligence and Neuroscience, 2020

View PDFchevron_right

BMPQ: Bit-Gradient Sensitivity-Driven Mixed-Precision Quantization of DNNs from Scratch

Qirui Sun

2022 Design, Automation & Test in Europe Conference & Exhibition (DATE)

View PDFchevron_right

Adaptive Precision Training (AdaPT): A dynamic quantized training approach for DNNs

Wilfried Gansterer

Society for Industrial and Applied Mathematics eBooks, 2023

View PDFchevron_right

Post training 4-bit quantization of convolutional networks for rapid-deployment

Ron Banner

2019

View PDFchevron_right

Improved Techniques for Quantizing Deep Networks with Adaptive Bit-Widths

Naigang Wang

2021

View PDFchevron_right

A Comprehensive Survey on Model Quantization for Deep Neural Networks

Ali Azarpeyvand

arXiv (Cornell University), 2022

View PDFchevron_right

A Fixed-Point Quantization Technique for Convolutional Neural Networks Based on Weight Scaling

Ralf Wittmann

2019 IEEE International Conference on Image Processing (ICIP)

View PDFchevron_right

Scalable Methods for 8-bit Training of Neural Networks

Ron Banner

2018

View PDFchevron_right

AdaQAT: Adaptive Bit-Width Quantization-Aware Training

Silviu-Ioan Filip

2024

View PDFchevron_right

SYQ: Learning Symmetric Quantization for Efficient Deep Neural Networks

Nicholas Fraser

2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2018

View PDFchevron_right

Adaptive Precision Training (AdaPT): A dynamic fixed point quantized training approach for DNNs

Wilfried Gansterer

2021

View PDFchevron_right

Learned Step Size Quantization

Deepika Bablani

ArXiv, 2020

View PDFchevron_right

BitPruning: Learning Bitlengths for Aggressive and Accurate Quantization

Milos Nikolic

Cornell University - arXiv, 2020

View PDFchevron_right

Blended coarse gradient descent for full quantization of deep neural networks

Jack Xin

Research in the Mathematical Sciences, 2019

View PDFchevron_right

ReLeQ : A Reinforcement Learning Approach for Automatic Deep Quantization of Neural Networks

Hadi Esmaeilzadeh

IEEE Micro

View PDFchevron_right

QDrop: Randomly Dropping Quantization for Extremely Low-bit Post-Training Quantization

Xiuying Wei

2022

View PDFchevron_right

Mix and Match: A Novel FPGA-Centric Deep Neural Network Quantization Framework

Hayden K H So

2021 IEEE International Symposium on High-Performance Computer Architecture (HPCA), 2021

View PDFchevron_right

FxP-QNet: A Post-Training Quantizer for the Design of Mixed Low-Precision DNNs With Dynamic Fixed-Point Representation

Aiman H. El-Maleh

IEEE Access, 2022

View PDFchevron_right

Power-of-Two Quantization for Low Bitwidth and Hardware Compliant Neural Networks

Barbara De Salvo

ArXiv, 2022

View PDFchevron_right

Differentiable Quantization of Deep Neural Networks

Thomas Kemp

ArXiv, 2019

View PDFchevron_right

Post-training Piecewise Linear Quantization for Deep Neural Networks

J Hass

Computer Vision – ECCV 2020, 2020

View PDFchevron_right

DoubleQExt: Hardware and Memory Efficient CNN Through Two Levels of Quantization

Hui-Fuang Ng

IEEE Access, 2021

View PDFchevron_right

Adaptive Precision Training (ADEPT): A dynamic fixed point quantized sparsifying training approach for DNNs

Wilfried Gansterer

2021

View PDFchevron_right

Quantizing Convolutional Neural Networks for Low-Power High-Throughput Inference Engines

Nicholas Fraser

ArXiv, 2018

View PDFchevron_right

BinaryRelax: A Relaxation Approach for Training Deep Neural Networks with Quantized Weights

Jack Xin

SIAM Journal on Imaging Sciences, 2018

View PDFchevron_right

Dither NN: Hardware/Algorithm Co-Design for Accurate Quantized Neural Networks

Masayuki Ikebe

IEICE Transactions on Information and Systems, 2019

View PDFchevron_right

HAWQ: Hessian AWare Quantization of Neural Networks with Mixed-Precision

Amir Gholami

In Proceedings of the IEEE International Conference on Computer Vision, 2019

View PDFchevron_right