English
Related papers

Related papers: Mixed Precision Post Training Quantization of Neur…

200 papers

Quantization for deep neural networks have afforded models for edge devices that use less on-board memory and enable efficient low-power inference. In this paper, we present a comparison of model-parameter driven quantization approaches…

Computer Vision and Pattern Recognition · Computer Science 2019-10-14 Prateeth Nayak , David Zhang , Sek Chai

For efficient neural network inference, it is desirable to achieve state-of-the-art accuracy with the simplest networks requiring the least computation, memory, and power. Quantizing networks to lower precision is a powerful technique for…

Machine Learning · Computer Science 2024-01-12 Deepika Bablani , Jeffrey L. Mckinstry , Steven K. Esser , Rathinakumar Appuswamy , Dharmendra S. Modha

Since model quantization helps to reduce the model size and computation latency, it has been successfully applied in many applications of mobile phones, embedded devices and smart chips. The mixed-precision quantization model can match…

Computer Vision and Pattern Recognition · Computer Science 2021-03-05 Qigong Sun , Licheng Jiao , Yan Ren , Xiufang Li , Fanhua Shang , Fang Liu

Sparse Mixture-of-Experts (MoE) allows scaling of language and vision models efficiently by activating only a small subset of experts per input. While this reduces computation, the large number of parameters still incurs substantial memory…

Model quantization has become a crucial technique to address the issues of large memory consumption and long inference times associated with LLMs. Mixed-precision quantization, which distinguishes between important and unimportant…

Machine Learning · Computer Science 2024-10-22 Yifan Tan , Haoze Wang , Chao Yan , Yangdong Deng

Quantization is a widely used technique to compress neural networks. Assigning uniform bit-widths across all layers can result in significant accuracy degradation at low precision and inefficiency at high precision. Mixed-precision…

Neural and Evolutionary Computing · Computer Science 2025-04-09 Zihao Deng , Sayeh Sharify , Xin Wang , Michael Orshansky

Recently, transformer has achieved remarkable performance on a variety of computer vision applications. Compared with mainstream convolutional neural networks, vision transformers are often of sophisticated architectures for extracting…

Computer Vision and Pattern Recognition · Computer Science 2021-06-29 Zhenhua Liu , Yunhe Wang , Kai Han , Siwei Ma , Wen Gao

LIDAR 3D object detection is one of the important tasks for autonomous vehicles. Ensuring that this task operates in real-time is crucial. Toward this, model quantization can be used to accelerate the runtime. However, directly applying…

Computer Vision and Pattern Recognition · Computer Science 2026-02-03 Ninnart Fuengfusin , Keisuke Yoneda , Naoki Suganuma

Convolutional Neural Networks (CNNs) have proven to be a powerful state-of-the-art method for image classification tasks. One drawback however is the high computational complexity and high memory consumption of CNNs which makes them…

Computer Vision and Pattern Recognition · Computer Science 2021-02-04 Rishabh Goyal , Joaquin Vanschoren , Victor van Acht , Stephan Nijssen

We propose a cluster-based quantization method to convert pre-trained full precision weights into ternary weights with minimal impact on the accuracy. In addition, we also constrain the activations to 8-bits thus enabling sub 8-bit full…

Machine Learning · Computer Science 2017-02-02 Naveen Mellempudi , Abhisek Kundu , Dipankar Das , Dheevatsa Mudigere , Bharat Kaul

Network quantization generally converts full-precision weights and/or activations into low-bit fixed-point values in order to accelerate an inference process. Recent approaches to network quantization further discretize the gradients into…

Computer Vision and Pattern Recognition · Computer Science 2024-07-18 Dohyung Kim , Junghyup Lee , Jeimin Jeon , Jaehyeon Moon , Bumsub Ham

We tackle the problem of producing compact models, maximizing their accuracy for a given model size. A standard solution is to train networks with Quantization Aware Training, where the weights are quantized during training and the…

Machine Learning · Computer Science 2021-03-02 Angela Fan , Pierre Stock , Benjamin Graham , Edouard Grave , Remi Gribonval , Herve Jegou , Armand Joulin

Currently, deep neural networks are deployed on low-power portable devices by first training a full-precision model using powerful hardware, and then deriving a corresponding low-precision model for efficient inference on such systems.…

Machine Learning · Computer Science 2017-11-15 Hao Li , Soham De , Zheng Xu , Christoph Studer , Hanan Samet , Tom Goldstein

Mixed-precision quantization of efficient networks often suffer from activation instability encountered in the exploration of bit selections. To address this problem, we propose a novel method called MetaMix which consists of bit selection…

Machine Learning · Computer Science 2024-04-10 Han-Byul Kim , Joo Hyung Lee , Sungjoo Yoo , Hong-Seok Kim

Large Language and Vision Models using a Mixture-of-Experts (MoE) architecture pose significant challenges for deployment due to their computational and memory demands. Mixed Precision Quantization assigns different precisions to different…

Machine Learning · Computer Science 2025-09-03 Krishna Teja Chitty-Venkata , Jie Ye , Murali Emani

Multi-bit quantization networks enable flexible deployment of deep neural networks by supporting multiple precision levels within a single model. However, existing approaches suffer from significant training overhead as full-dataset updates…

Computer Vision and Pattern Recognition · Computer Science 2025-10-24 Jinhee Kim , Jae Jun An , Kang Eun Jeon , Jong Hwan Ko

Deep networks run with low precision operations at inference time offer power and space advantages over high precision alternatives, but need to overcome the challenge of maintaining high accuracy as precision decreases. Here, we present a…

Machine Learning · Computer Science 2020-05-08 Steven K. Esser , Jeffrey L. McKinstry , Deepika Bablani , Rathinakumar Appuswamy , Dharmendra S. Modha

Tensor decomposition of convolutional and fully-connected layers is an effective way to reduce parameters and FLOP in neural networks. Due to memory and power consumption limitations of mobile or embedded devices, the quantization step is…

Machine Learning · Computer Science 2023-08-10 Daria Cherniuk , Stanislav Abukhovich , Anh-Huy Phan , Ivan Oseledets , Andrzej Cichocki , Julia Gusak

The large computing and memory cost of deep neural networks (DNNs) often precludes their use in resource-constrained devices. Quantizing the parameters and operations to lower bit-precision offers substantial memory and energy savings for…

Machine Learning · Computer Science 2023-09-01 Clemens JS Schaefer , Siddharth Joshi , Shan Li , Raul Blazquez

In this paper, we seek to tackle a challenge in training low-precision networks: the notorious difficulty in propagating gradient through a low-precision network due to the non-differentiable quantization function. We propose a solution by…

Computer Vision and Pattern Recognition · Computer Science 2020-03-19 Bohan Zhuang , Lingqiao Liu , Mingkui Tan , Chunhua Shen , Ian Reid