English
Related papers

Related papers: Where and How to Enhance: Discovering Bit-Width Co…

200 papers

In this paper, we propose Mix-QViT, an explainability-driven MPQ framework that systematically allocates bit-widths to each layer based on two criteria: layer importance, assessed via Layer-wise Relevance Propagation (LRP), which identifies…

Computer Vision and Pattern Recognition · Computer Science 2025-01-14 Navin Ranjan , Andreas Savakis

Quantization is essential for Neural Network (NN) compression, reducing model size and computational demands by using lower bit-width data types, though aggressive reduction often hampers accuracy. Mixed Precision (MP) mitigates this…

Machine Learning · Computer Science 2025-05-20 Shmulik Markovich-Golan , Daniel Ohayon , Itay Niv , Yair Hanani

Mixed-precision quantization has received increasing attention for its capability of reducing the computational burden and speeding up the inference time. Existing methods usually focus on the sensitivity of different network layers, which…

Computer Vision and Pattern Recognition · Computer Science 2022-12-21 Mingkai Wang , Taisong Jin , Miaohui Zhang , Zhengtao Yu

Quantizing neural networks is one of the most effective methods for achieving efficient inference on mobile and embedded devices. In particular, mixed precision quantized (MPQ) networks, whose layers can be quantized to different bitwidths,…

Machine Learning · Computer Science 2023-07-11 Jorn Peters , Marios Fournarakis , Markus Nagel , Mart van Baalen , Tijmen Blankevoort

Efficient model inference is an important and practical issue in the deployment of deep neural network on resource constraint platforms. Network quantization addresses this problem effectively by leveraging low-bit representation and…

Computer Vision and Pattern Recognition · Computer Science 2020-01-01 Tianshu Chu , Qin Luo , Jie Yang , Xiaolin Huang

How can we accurately quantize a pre-trained Vision Transformer model? Quantization algorithms compress Vision Transformers (ViTs) into low-bit formats, reducing memory and computation demands with minimal accuracy degradation. However,…

Computer Vision and Pattern Recognition · Computer Science 2025-11-17 Minjun Kim , Jaeri Lee , Jongjin Kim , Jeongin Yun , Yongmo Kwon , U Kang

As deep neural networks (DNNs) see increased deployment on mobile and edge devices, optimizing model efficiency has become crucial. Mixed-precision quantization is widely favored, as it offers a superior balance between efficiency and…

Machine Learning · Computer Science 2025-07-31 Seokho Han , Seoyeon Yoon , Jinhee Kim , Dongwei Wang , Kang Eun Jeon , Huanrui Yang , Jong Hwan Ko

Post-Training Quantization (PTQ) is pivotal for deploying large language models (LLMs) within resource-limited settings by significantly reducing resource demands. However, existing PTQ strategies underperform at low bit levels < 3 bits due…

Computation and Language · Computer Science 2025-01-31 Wanlong Liu , Yichen Xiao , Dingyi Zeng , Hongyang Zhao , Wenyu Chen , Malu Zhang

Large Language Models (LLMs) promise impressive capabilities, yet their multi-billion-parameter scale makes on-device or low-resource deployment prohibitive. Mixed-precision quantization offers a compelling solution, but existing methods…

Machine Learning · Computer Science 2025-12-16 Junchen Zhao , Ali Derakhshan , Jayden Kana Hyman , Junhao Dong , Sangeetha Abdu Jyothi , Ian Harris

Quantization is a widely used technique to compress and accelerate deep neural networks. However, conventional quantization methods use the same bit-width for all (or most of) the layers, which often suffer significant accuracy degradation…

Computer Vision and Pattern Recognition · Computer Science 2021-10-14 Weihan Chen , Peisong Wang , Jian Cheng

Mixed-precision quantization, where a deep neural network's layers are quantized to different precisions, offers the opportunity to optimize the trade-offs between model size, latency, and statistical accuracy beyond what can be achieved…

Machine Learning · Computer Science 2023-07-07 Georg Rutishauser , Francesco Conti , Luca Benini

Mixture-of-Experts Large Language Models (MoE-LLMs) achieve strong performance but incur substantial memory overhead due to massive expert parameters. Mixed-precision quantization mitigates this cost by allocating expert-wise bit-widths…

Machine Learning · Computer Science 2026-05-25 Jianing Deng , Song Wang , Dongwei Wang , Zijie Liu , Tianlong Chen , Huanrui Yang , Jingtong Hu

Quantization is widely employed in both cloud and edge systems to reduce the memory occupation, latency, and energy consumption of deep neural networks. In particular, mixed-precision quantization, i.e., the use of different bit-widths for…

Machine Learning · Computer Science 2023-01-26 Matteo Risso , Alessio Burrello , Luca Benini , Enrico Macii , Massimo Poncino , Daniele Jahier Pagliari

Quantized Neural Networks (QNN) with extremely low-bitwidth data have proven promising in efficient storage and computation on edge devices. To further reduce the accuracy drop while increasing speedup, layer-wise mixed-precision…

Machine Learning · Computer Science 2025-08-14 Zijun Jiang , Yangdi Lyu

Today, large language models have demonstrated their strengths in various tasks ranging from reasoning, code generation, and complex problem solving. However, this advancement comes with a high computational cost and memory requirements,…

Machine Learning · Computer Science 2026-03-26 Meriem Bouzouad , Yuan-Hao Chang , Jalil Boukhobza

The Segment Anything Model (SAM) is a popular vision foundation model; however, its high computational and memory demands make deployment on resource-constrained devices challenging. While Post-Training Quantization (PTQ) is a practical…

Computer Vision and Pattern Recognition · Computer Science 2025-05-09 Navin Ranjan , Andreas Savakis

Efficient deep neural network (DNN) inference on mobile or embedded devices typically involves quantization of the network parameters and activations. In particular, mixed precision networks achieve better performance than networks with…

Model quantization is challenging due to many tedious hyper-parameters such as precision (bitwidth), dynamic range (minimum and maximum discrete values) and stepsize (interval between discrete values). Unlike prior arts that carefully tune…

Machine Learning · Computer Science 2021-07-08 Zhang Zhaoyang , Shao Wenqi , Gu Jinwei , Wang Xiaogang , Luo Ping

As an effective technique to achieve the implementation of deep neural networks in edge devices, model quantization has been successfully applied in many practical applications. No matter the methods of quantization aware training (QAT) or…

Computer Vision and Pattern Recognition · Computer Science 2021-05-05 Qigong Sun , Xiufang Li , Yan Ren , Zhongjian Huang , Xu Liu , Licheng Jiao , Fang Liu

One of the most significant bottleneck in training large scale machine learning models on parameter server (PS) is the communication overhead, because it needs to frequently exchange the model gradients between the workers and servers…

Machine Learning · Computer Science 2018-04-25 Guoxin Cui , Jun Xu , Wei Zeng , Yanyan Lan , Jiafeng Guo , Xueqi Cheng