English
Related papers

Related papers: EQO: Exploring Ultra-Efficient Private Inference w…

200 papers

Private convolutional neural network (CNN) inference based on secure two-party computation (2PC) suffers from high communication and latency overhead, especially from convolution layers. In this paper, we propose UFO, a quantized 2PC…

Cryptography and Security · Computer Science 2026-02-24 Wenxuan Zeng , Chao Yang , Tianshi Xu , Bo Zhang , Changrui Ren , Jin Dong , Meng Li

Deep neural network (DNN) inference based on secure 2-party computation (2PC) can offer cryptographically-secure privacy protection but suffers from orders of magnitude latency overhead due to enormous communication. Previous works heavily…

Cryptography and Security · Computer Science 2023-11-06 Wenxuan Zeng , Meng Li , Haichuan Yang , Wen-jie Lu , Runsheng Wang , Ru Huang

Private deep neural network (DNN) inference based on secure two-party computation (2PC) enables secure privacy protection for both the server and the client. However, existing secure 2PC frameworks suffer from a high inference latency due…

Cryptography and Security · Computer Science 2024-10-15 Tianshi Xu , Shuzhang Zhong , Wenxuan Zeng , Runsheng Wang , Meng Li

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

The 8 bits quantization has been widely applied to accelerate network inference in various deep learning applications. There are two kinds of quantization methods, training-based quantization and post-training quantization. Training-based…

Computer Vision and Pattern Recognition · Computer Science 2020-07-01 Di Wu , Qi Tang , Yongle Zhao , Ming Zhang , Ying Fu , Debing Zhang

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

Convolution is the core operation for many deep neural networks. The Winograd convolution algorithms have been shown to accelerate the widely-used small convolution sizes. Quantized neural networks can effectively reduce model sizes and…

Neural and Evolutionary Computing · Computer Science 2019-01-09 Lingchuan Meng , John Brothers

Accelerating deep convolutional neural networks has become an active topic and sparked an interest in academia and industry. In this paper, we propose an efficient low-precision quantized Winograd convolution algorithm, called LANCE, which…

Computer Vision and Pattern Recognition · Computer Science 2020-07-29 Guangli Li , Lei Liu , Xueying Wang , Xiu Ma , Xiaobing Feng

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

Convolution is the most time-consuming part in the computation of convolutional neural networks (CNNs), which have achieved great successes in numerous applications. Due to the complex data dependency and the increase in the amount of model…

Machine Learning · Computer Science 2021-01-01 Xiaoyang Zhang , Junmin Xiao , Guangming Tan

Despite the revolutionary breakthroughs of large-scale text-to-image diffusion models for complex vision and downstream tasks, their extremely high computational and storage costs limit their usability. Quantization of diffusion models has…

Computer Vision and Pattern Recognition · Computer Science 2025-04-02 Shuokai Pan , Gerti Tuzi , Sudarshan Sreeram , Dibakar Gope

Prior research has shown that Winograd algorithm can reduce the computational complexity of convolutional neural networks (CNN) with weights and activations represented in floating point. However it is difficult to apply the scheme to the…

Machine Learning · Computer Science 2020-07-27 Zhi-Gang Liu , Matthew Mattina

Convolutional neural networks (CNNs) have dramatically improved the accuracy of tasks such as object recognition, image segmentation and interactive speech systems. CNNs require large amounts of computing resources because ofcomputationally…

Computer Vision and Pattern Recognition · Computer Science 2022-01-26 Syed Asad Alam , Andrew Anderson , Barbara Barabasz , David Gregg

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

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

Fast convolution algorithms, including Winograd and FFT, can efficiently accelerate convolution operations in deep models. However, these algorithms depend on high-precision arithmetic to maintain inference accuracy, which conflicts with…

Machine Learning · Computer Science 2024-07-04 Liulu He , Yufei Zhao , Rui Gao , Yuan Du , Li Du

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

Deep neural networks (DNNs) can be made hardware-efficient by reducing the numerical precision of the weights and activations of the network and by improving the network's resilience to noise. However, this gain in efficiency often comes at…

This paper presents a novel network compression framework Kernel Quantization (KQ), targeting to efficiently convert any pre-trained full-precision convolutional neural network (CNN) model into a low-precision version without significant…

Machine Learning · Computer Science 2020-03-12 Zhongzhi Yu , Yemin Shi , Tiejun Huang , Yizhou Yu

Current model quantization methods have shown their promising capability in reducing storage space and computation complexity. However, due to the diversity of quantization forms supported by different hardware, one limitation of existing…

Computer Vision and Pattern Recognition · Computer Science 2023-08-16 Ke Xu , Lei Han , Ye Tian , Shangshang Yang , Xingyi Zhang
‹ Prev 1 2 3 10 Next ›