English
Related papers

Related papers: DWM: A Decomposable Winograd Method for Convolutio…

200 papers

Deep convolutional neural networks (ConvNets) of 3-dimensional kernels allow joint modeling of spatiotemporal features. These networks have improved performance of video and volumetric image analysis, but have been limited in size due to…

Computer Vision and Pattern Recognition · Computer Science 2017-06-13 David Budden , Alexander Matveev , Shibani Santurkar , Shraman Ray Chaudhuri , Nir Shavit

Very deep convolutional neural networks (CNNs) have been firmly established as the primary methods for many computer vision tasks. However, most state-of-the-art CNNs are large, which results in high inference latency. Recently, depth-wise…

Computer Vision and Pattern Recognition · Computer Science 2025-01-07 Yihui He , Jianing Qian , Jianren Wang , Cindy X. Le , Congrui Hetang , Qi Lyu , Wenping Wang , Tianwei Yue

Deep convolutional neural networks take GPU days of compute time to train on large data sets. Pedestrian detection for self driving cars requires very low latency. Image recognition for mobile phones is constrained by limited processing…

Neural and Evolutionary Computing · Computer Science 2015-11-11 Andrew Lavin , Scott Gray

Sparse methods and the use of Winograd convolutions are two orthogonal approaches, each of which significantly accelerates convolution computations in modern CNNs. Sparse Winograd merges these two and thus has the potential to offer a…

Computer Vision and Pattern Recognition · Computer Science 2017-10-17 Sheng Li , Jongsoo Park , Ping Tak Peter Tang

This paper focuses on Winograd transformation in 3D convolutional neural networks (CNNs) that are more over-parameterized compared with the 2D version. The over-increasing Winograd parameters not only exacerbate training complexity but also…

Computer Vision and Pattern Recognition · Computer Science 2023-01-27 Ziran Qin , Mingbao Lin , Weiyao Lin

This article provides next step towards solving speed bottleneck of any system that intensively uses convolutions operations (e.g. CNN). Method described in the article is applied on deformable part models (DPM) algorithm. Method described…

Computer Vision and Pattern Recognition · Computer Science 2017-07-12 D. V. Parkhomenko , I. L. Mazurenko

The problem how to speed up the convolution computations in Deep Neural Networks is widely investigated in recent years. The Winograd convolution algorithm is a common used method that significantly reduces time consumption. However, it…

Machine Learning · Computer Science 2020-04-24 Barbara Barabasz

Adder neural network (AdderNet) is a new kind of deep model that replaces the original massive multiplications in convolutions by additions while preserving the high performance. Since the hardware complexity of additions is much lower than…

Machine Learning · Computer Science 2021-05-13 Wenshuo Li , Hanting Chen , Mingqiang Huang , Xinghao Chen , Chunjing Xu , Yunhe Wang

The prevalence of convolution in applications within signal processing, deep neural networks, and numerical solvers has motivated the development of numerous fast convolution algorithms. In many of these problems, convolution is performed…

Numerical Analysis · Mathematics 2020-07-03 Caleb Ju , Edgar Solomonik

The Winograd or Cook-Toom class of algorithms help to reduce the overall compute complexity of many modern deep convolutional neural networks (CNNs). Although there has been a lot of research done on model and algorithmic optimization of…

Machine Learning · Computer Science 2019-03-06 Partha Maji , Andrew Mundy , Ganesh Dasika , Jesse Beu , Matthew Mattina , Robert Mullins

The deployment of deep convolutional neural networks (CNNs) in many real world applications is largely hindered by their high computational cost. In this paper, we propose a novel learning scheme for CNNs to simultaneously 1) reduce the…

Computer Vision and Pattern Recognition · Computer Science 2017-08-23 Zhuang Liu , Jianguo Li , Zhiqiang Shen , Gao Huang , Shoumeng Yan , Changshui Zhang

Deep neural networks (DNNs) require very large amounts of computation both for training and for inference when deployed in the field. A common approach to implementing DNNs is to recast the most computationally expensive operations as…

Computer Vision and Pattern Recognition · Computer Science 2017-09-12 Andrew Anderson , Aravind Vasudevan , Cormac Keane , David Gregg

Deep convolutional neural networks (CNNs) with a large number of parameters require intensive computational resources, and thus are hard to be deployed in resource-constrained platforms. Decomposition-based methods, therefore, have been…

Computer Vision and Pattern Recognition · Computer Science 2022-10-27 Shaowu Chen , Jiahao Zhou , Weize Sun , Lei Huang

Previous works utilized ''smaller-norm-less-important'' criterion to prune filters with smaller norm values in a convolutional neural network. In this paper, we analyze this norm-based criterion and point out that its effectiveness depends…

Computer Vision and Pattern Recognition · Computer Science 2019-07-16 Yang He , Ping Liu , Ziwei Wang , Zhilan Hu , Yi Yang

Large CNNs have delivered impressive performance in various computer vision applications. But the storage and computation requirements make it problematic for deploying these models on mobile devices. Recently, tensor decompositions have…

Machine Learning · Computer Science 2016-02-16 Cheng Tai , Tong Xiao , Yi Zhang , Xiaogang Wang , Weinan E

Deep convolution Neural Network (DCNN) has been widely used in computer vision tasks. However, for edge devices even inference has too large computational complexity and data access amount. The inference latency of state-of-the-art models…

Hardware Architecture · Computer Science 2025-09-09 Kuan-Ting Lin , Ching-Te Chiu , Jheng-Yi Chang , Shi-Zong Huang , Yu-Ting Li

Convolutional neural networks (CNNs) have shown remarkable performance in various computer vision tasks in recent years. However, the increasing model size has raised challenges in adopting them in real-time applications as well as mobile…

Computer Vision and Pattern Recognition · Computer Science 2018-11-20 Van-Thanh Hoang , Kang-Hyun Jo

The recently established Convolution Nuclear Norm Minimization (CNNM) addresses the problem of \textit{tensor completion with arbitrary sampling} (TCAS), which involves restoring a tensor from a subset of its entries sampled in an arbitrary…

Computer Vision and Pattern Recognition · Computer Science 2026-04-21 Wei Li , Yuyang Li , Kaile Du , Yi Yu , Guangcan Liu

Depthwise separable convolution has shown great efficiency in network design, but requires time-consuming training procedure with full training-set available. This paper first analyzes the mathematical relationship between regular…

Computer Vision and Pattern Recognition · Computer Science 2018-08-17 Jianbo Guo , Yuxi Li , Weiyao Lin , Yurong Chen , Jianguo Li

With their high energy efficiency, processing-in-memory (PIM) arrays are increasingly used for convolutional neural network (CNN) inference. In PIM-based CNN inference, the computational latency and energy are dependent on how the CNN…

Machine Learning · Computer Science 2021-12-22 Johnny Rhe , Sungmin Moon , Jong Hwan Ko