English
Related papers

Related papers: CoDeQ: End-to-End Joint Model Compression with Dea…

200 papers

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

Modern deployment often requires trading accuracy for efficiency under tight CPU and memory constraints, yet common compression proxies such as parameter count or FLOPs do not reliably predict wall-clock inference time. In particular,…

Machine Learning · Computer Science 2026-04-10 Longsheng Zhou , Yu Shen

A low-precision analog-to-digital converter (ADC) is required to implement a frontend device of wideband digital communication systems in order to reduce its power consumption. The goal of this paper is to present a novel joint quantizer…

Information Theory · Computer Science 2018-04-18 Tadashi Wadayama , Satoshi Takabe

Deep Neural Networks(DNNs) have many parameters and activation data, and these both are expensive to implement. One method to reduce the size of the DNN is to quantize the pre-trained model by using a low-bit expression for weights and…

Computer Vision and Pattern Recognition · Computer Science 2020-11-26 Jun Nishikawa , Ryoji Ikegaya

When approaching a novel visual recognition problem in a specialized image domain, a common strategy is to start with a pre-trained deep neural network and fine-tune it to the specialized domain. If the target domain covers a smaller visual…

Computer Vision and Pattern Recognition · Computer Science 2017-07-31 Frederick Tung , Srikanth Muralidharan , Greg Mori

For unsupervised data-dependent hashing, the two most important requirements are to preserve similarity in the low-dimensional feature space and to minimize the binary quantization loss. A well-established hashing approach is Iterative…

Computer Vision and Pattern Recognition · Computer Science 2019-11-14 Tuan Hoang , Thanh-Toan Do , Huu Le , Dang-Khoa Le-Tan , Ngai-Man Cheung

This paper presents incremental network quantization (INQ), a novel method, targeting to efficiently convert any pre-trained full-precision convolutional neural network (CNN) model into a low-precision version whose weights are constrained…

Computer Vision and Pattern Recognition · Computer Science 2017-08-28 Aojun Zhou , Anbang Yao , Yiwen Guo , Lin Xu , Yurong Chen

Low-bit quantization has become widespread for compressing image super-resolution (SR) models for edge deployment, which allows advanced SR models to enjoy compact low-bit parameters and efficient integer/bitwise constructions for storage…

Image and Video Processing · Electrical Eng. & Systems 2024-06-12 Kai Liu , Haotong Qin , Yong Guo , Xin Yuan , Linghe Kong , Guihai Chen , Yulun Zhang

In this work, we developed and tested 3 techniques for vector quantization (VQ) based model weight compression. To mitigate codebook collapse and enable end-to-end training, we adopted cosine similarity-based assignment. Building on ideas…

Machine Learning · Computer Science 2026-04-28 Terry Gou , Puneet Gupta

Although weight and activation quantization is an effective approach for Deep Neural Network (DNN) compression and has a lot of potentials to increase inference speed leveraging bit-operations, there is still a noticeable gap in terms of…

Computer Vision and Pattern Recognition · Computer Science 2018-07-27 Dongqing Zhang , Jiaolong Yang , Dongqiangzi Ye , Gang Hua

Designing neural architectures is a fundamental step in deep learning applications. As a partner technique, model compression on neural networks has been widely investigated to gear the needs that the deep learning algorithms could be run…

Computer Vision and Pattern Recognition · Computer Science 2018-11-26 Yukang Chen , Gaofeng Meng , Qian Zhang , Xinbang Zhang , Liangchen Song , Shiming Xiang , Chunhong Pan

Network quantization is a powerful technique to compress convolutional neural networks. The quantization granularity determines how to share the scaling factors in weights, which affects the performance of network quantization. Most…

Computer Vision and Pattern Recognition · Computer Science 2021-10-19 Zhihang Yuan , Yiqi Chen , Chenhao Xue , Chenguang Zhang , Qiankun Wang , Guangyu Sun

Mixed Precision Quantization (MPQ) has become an essential technique for optimizing neural network by determining the optimal bitwidth per layer. Existing MPQ methods, however, face a major hurdle: they require a computationally expensive…

Computer Vision and Pattern Recognition · Computer Science 2025-05-20 Lianbo Ma , Jianlun Ma , Yuee Zhou , Guoyang Xie , Qiang He , Zhichao Lu

Large language models (LLMs) have significantly advanced the natural language processing paradigm but impose substantial demands on memory and computational resources. Quantization is one of the most effective ways to reduce memory…

Machine Learning · Computer Science 2025-04-29 Xilong Xie , Liang Wang , Limin Xiao , Meng Han , Lin Sun , Shuai Zheng , Xiangrong Xu

Quantization and pruning are two effective Deep Neural Networks model compression methods. In this paper, we propose Automatic Prune Binarization (APB), a novel compression technique combining quantization with pruning. APB enhances the…

Computer Vision and Pattern Recognition · Computer Science 2023-09-18 Franco Maria Nardini , Cosimo Rulli , Salvatore Trani , Rossano Venturini

To facilitate efficient embedded and hardware implementations of deep neural networks (DNNs), two important categories of DNN model compression techniques: weight pruning and weight quantization are investigated. The former leverages the…

Machine Learning · Computer Science 2019-01-03 Ao Ren , Tianyun Zhang , Shaokai Ye , Jiayu Li , Wenyao Xu , Xuehai Qian , Xue Lin , Yanzhi Wang

To reduce model size during post-training, compression methods, including knowledge distillation, low-rank approximation, and pruning, are often applied after fine-tuning the model. However, sequential fine-tuning and compression sacrifices…

Machine Learning · Computer Science 2025-05-29 Xiangyu Chen , Jing Liu , Ye Wang , Matthew Brand , Pu , Wang , Toshiaki Koike-Akino

Network quantization is an effective solution to compress deep neural networks for practical usage. Existing network quantization methods cannot sufficiently exploit the depth information to generate low-bit compressed network. In this…

Machine Learning · Computer Science 2018-12-18 Yuhui Xu , Yongzhuang Wang , Aojun Zhou , Weiyao Lin , Hongkai Xiong

Model quantization is a widely used technique to compress and accelerate deep neural network (DNN) inference. Emergent DNN hardware accelerators begin to support mixed precision (1-8 bits) to further improve the computation efficiency,…

Computer Vision and Pattern Recognition · Computer Science 2020-08-14 Kuan Wang , Zhijian Liu , Yujun Lin , Ji Lin , Song Han

The deployment of deep neural networks on resource-constrained devices necessitates effective model com- pression strategies that judiciously balance the reduction of model size with the preservation of performance. This study introduces a…

Machine Learning · Computer Science 2025-05-02 Mohammad Zbeeb , Mariam Salman , Mohammad Bazzi , Ammar Mohanna