English
Related papers

Related papers: Efficient Bitwidth Search for Practical Mixed Prec…

200 papers

Post-training weight quantization is crucial for reducing the memory and inference cost of large language models (LLMs), yet pushing the average precision below 4 bits remains challenging due to highly non-uniform weight sensitivity and the…

Machine Learning · Computer Science 2026-02-23 Xinlin Li , Timothy Chou , Josh Fromm , Zichang Liu , Yunjie Pan , Christina Fragouli

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

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…

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

Deploying mixed-precision neural networks on edge devices is friendly to hardware resources and power consumption. To support fully mixed-precision neural network inference, it is necessary to design flexible hardware accelerators for…

Hardware Architecture · Computer Science 2025-02-04 Liang Zhao , Kunming Shao , Fengshi Tian , Tim Kwang-Ting Cheng , Chi-Ying Tsui , Yi Zou

Quantization has been proven to be a vital method for improving the inference efficiency of deep neural networks (DNNs). However, it is still challenging to strike a good balance between accuracy and efficiency while quantizing DNN weights…

Computer Vision and Pattern Recognition · Computer Science 2021-11-25 Cheng Gong , Ye Lu , Kunpeng Xie , Zongming Jin , Tao Li , Yanzhi Wang

Binary Neural Networks (BNNs) are showing tremendous success on realistic image classification tasks. Notably, their accuracy is similar to the state-of-the-art accuracy obtained by full-precision models tailored to edge devices. In this…

Hardware Architecture · Computer Science 2022-12-02 Franyell Silfa , Jose Maria Arnau , Antonio González

Mixed-precision Deep Neural Networks achieve the energy efficiency and throughput needed for hardware deployment, particularly when the resources are limited, without sacrificing accuracy. However, the optimal per-layer bit precision that…

Machine Learning · Computer Science 2022-08-15 Mariam Rakka , Mohammed E. Fouda , Pramod Khargonekar , Fadi Kurdahi

Mixed-precision networks allow for a variable bit-width quantization for every layer in the network. A major limitation of existing work is that the bit-width for each layer must be predefined during training time. This allows little…

Machine Learning · Computer Science 2021-04-01 Adrian Bulat , Georgios Tzimiropoulos

Binarization is an extreme network compression approach that provides large computational speedups along with energy and memory savings, albeit at significant accuracy costs. We investigate the question of where to binarize inputs at…

Computer Vision and Pattern Recognition · Computer Science 2018-04-12 Ameya Prabhu , Vishal Batchu , Rohit Gajawada , Sri Aurobindo Munagala , Anoop Namboodiri

Recent machine learning methods use increasingly large deep neural networks to achieve state of the art results in various tasks. The gains in performance come at the cost of a substantial increase in computation and storage requirements.…

Machine Learning · Computer Science 2019-03-26 Yoni Choukroun , Eli Kravchik , Fan Yang , Pavel Kisilev

Binarized neural networks, or BNNs, show great promise in edge-side applications with resource limited hardware, but raise the concerns of reduced accuracy. Motivated by the complex neural networks, in this paper we introduce complex…

Neural and Evolutionary Computing · Computer Science 2021-04-21 Yanfei Li , Tong Geng , Ang Li , Huimin Yu

Quantized neural networks with low-bit weights and activations are attractive for developing AI accelerators. However, the quantization functions used in most conventional quantization methods are non-differentiable, which increases the…

Computer Vision and Pattern Recognition · Computer Science 2020-09-21 Zhaohui Yang , Yunhe Wang , Kai Han , Chunjing Xu , Chao Xu , Dacheng Tao , Chang Xu

The resource requirements of deep neural networks (DNNs) pose significant challenges to their deployment on edge devices. Common approaches to address this issue are pruning and mixed-precision quantization, which lead to latency and memory…

We introduce a novel scheme to train binary convolutional neural networks (CNNs) -- CNNs with weights and activations constrained to {-1,+1} at run-time. It has been known that using binary weights and activations drastically reduce memory…

Machine Learning · Computer Science 2017-12-01 Xiaofan Lin , Cong Zhao , Wei Pan

Traditional neural architecture search (NAS) has a significant impact in computer vision by automatically designing network architectures for various tasks. In this paper, binarized neural architecture search (BNAS), with a search space of…

Computer Vision and Pattern Recognition · Computer Science 2020-09-10 Hanlin Chen , Li'an Zhuo , Baochang Zhang , Xiawu Zheng , Jianzhuang Liu , Rongrong Ji , David Doermann , Guodong Guo

Energy efficiency and memory footprint of a convolutional neural network (CNN) implemented on a CNN inference accelerator depend on many factors, including a weight quantization strategy (i.e., data types and bit-widths) and mapping (i.e.,…

Hardware Architecture · Computer Science 2025-07-23 Jan Klhufek , Miroslav Safar , Vojtech Mrazek , Zdenek Vasicek , Lukas Sekanina

In this paper, we propose to train a network with binary weights and low-bitwidth activations, designed especially for mobile devices with limited power consumption. Most previous works on quantizing CNNs uncritically assume the same…

Computer Vision and Pattern Recognition · Computer Science 2018-08-09 Bohan Zhuang , Chunhua Shen , Ian Reid

Deep neural networks, such as the Deep-FSMN, have been widely studied for keyword spotting (KWS) applications while suffering expensive computation and storage. Therefore, network compression technologies like binarization are studied to…

Computation and Language · Computer Science 2023-02-07 Haotong Qin , Xudong Ma , Yifu Ding , Xiaoyang Li , Yang Zhang , Zejun Ma , Jiakai Wang , Jie Luo , Xianglong Liu

Searching for a more compact network width recently serves as an effective way of channel pruning for the deployment of convolutional neural networks (CNNs) under hardware constraints. To fulfill the searching, a one-shot supernet is…

Computer Vision and Pattern Recognition · Computer Science 2021-05-25 Xiu Su , Shan You , Fei Wang , Chen Qian , Changshui Zhang , Chang Xu