English
Related papers

Related papers: XSepConv: Extremely Separated Convolution

200 papers

Compact neural networks are inclined to exploit "sparsely-connected" convolutions such as depthwise convolution and group convolution for employment in mobile applications. Compared with standard "fully-connected" convolutions, these…

Computer Vision and Pattern Recognition · Computer Science 2018-03-28 Zheng Qin , Zhaoning Zhang , Shiqing Zhang , Hao Yu , Yuxing Peng

Deep neural networks are increasingly used on mobile devices, where computational resources are limited. In this paper we develop CondenseNet, a novel network architecture with unprecedented efficiency. It combines dense connectivity with a…

Computer Vision and Pattern Recognition · Computer Science 2018-06-08 Gao Huang , Shichen Liu , Laurens van der Maaten , Kilian Q. Weinberger

Traditional 3D convolutions are computationally expensive, memory intensive, and due to large number of parameters, they often tend to overfit. On the other hand, 2D CNNs are less computationally expensive and less memory intensive than 3D…

Computer Vision and Pattern Recognition · Computer Science 2019-09-10 Gagan Kanojia , Sudhakar Kumawat , Shanmuganathan Raman

In this paper, we study the problem of designing efficient convolutional neural network architectures with the interest in eliminating the redundancy in convolution kernels. In addition to structured sparse kernels, low-rank kernels and the…

Computer Vision and Pattern Recognition · Computer Science 2018-04-18 Guotian Xie , Jingdong Wang , Ting Zhang , Jianhuang Lai , Richang Hong , Guo-Jun Qi

One of recent trends [30, 31, 14] in network architec- ture design is stacking small filters (e.g., 1x1 or 3x3) in the entire network because the stacked small filters is more ef- ficient than a large kernel, given the same computational…

Computer Vision and Pattern Recognition · Computer Science 2017-03-09 Chao Peng , Xiangyu Zhang , Gang Yu , Guiming Luo , Jian Sun

As a basic component of SE(3)-equivariant deep feature learning, steerable convolution has recently demonstrated its advantages for 3D semantic analysis. The advantages are, however, brought by expensive computations on dense, volumetric…

Computer Vision and Pattern Recognition · Computer Science 2021-11-16 Jiehong Lin , Hongyang Li , Ke Chen , Jiangbo Lu , Kui Jia

Recent studies focus on developing efficient systems for acoustic scene classification (ASC) using convolutional neural networks (CNNs), which typically consist of consecutive kernels. This paper highlights the benefits of using separate…

Sound · Computer Science 2024-05-30 Yiqiang Cai , Peihong Zhang , Shengchen Li

The recent researches in Deep Convolutional Neural Network have focused their attention on improving accuracy that provide significant advances. However, if they were limited to classification tasks, nowadays with contributions from…

Computer Vision and Pattern Recognition · Computer Science 2017-11-16 Geraldin Nanfack , Azeddine Elhassouny , Rachid Oulad Haj Thami

To efficiently extract spatiotemporal features of video for action recognition, most state-of-the-art methods integrate 1D temporal convolution into a conventional 2D CNN backbone. However, they all exploit 1D temporal convolution of fixed…

Computer Vision and Pattern Recognition · Computer Science 2020-01-28 Kaiyu Shan , Yongtao Wang , Zhuoying Wang , Tingting Liang , Zhi Tang , Ying Chen , Yangyan Li

When deploying a deep neural network on constrained hardware, it is possible to replace the network's standard convolutions with grouped convolutions. This allows for substantial memory savings with minimal loss of accuracy. However,…

Machine Learning · Computer Science 2020-06-18 Perry Gibson , José Cano , Jack Turner , Elliot J. Crowley , Michael O'Boyle , Amos Storkey

Weight pruning is among the most popular approaches for compressing deep convolutional neural networks. Recent work suggests that in a randomly initialized deep neural network, there exist sparse subnetworks that achieve performance…

Computer Vision and Pattern Recognition · Computer Science 2022-10-25 Vinay Kumar Verma , Nikhil Mehta , Shijing Si , Ricardo Henao , Lawrence Carin

Convolutional neural networks (CNNs) have constantly achieved better performance over years by introducing more complex topology, and enlarging the capacity towards deeper and wider CNNs. This makes the manual design of CNNs extremely…

Computer Vision and Pattern Recognition · Computer Science 2022-12-09 Bin Wang , Bing Xue , Mengjie Zhang

In order to handle modern convolutional neural networks (CNNs) efficiently, a hardware architecture of CNN inference accelerator is proposed to handle depthwise convolutions and regular convolutions, which are both essential building blocks…

Computer Vision and Pattern Recognition · Computer Science 2021-04-30 Tse-Wei Chen , Wei Tao , Deyu Wang , Dongchao Wen , Kinya Osa , Masami Kato

Convolutional neural networks (CNNs) have made resounding success in many computer vision tasks such as image classification and object detection. However, their performance degrades rapidly on tougher tasks where images are of low…

Computer Vision and Pattern Recognition · Computer Science 2022-08-09 Raja Sunkara , Tie Luo

Many effective solutions have been proposed to reduce the redundancy of models for inference acceleration. Nevertheless, common approaches mostly focus on eliminating less important filters or constructing efficient operations, while…

Computer Vision and Pattern Recognition · Computer Science 2020-06-23 Qiulin Zhang , Zhuqing Jiang , Qishuo Lu , Jia'nan Han , Zhengxin Zeng , Shang-hua Gao , Aidong Men

Transformers have quickly shined in the computer vision world since the emergence of Vision Transformers (ViTs). The dominant role of convolutional neural networks (CNNs) seems to be challenged by increasingly effective transformer-based…

Computer Vision and Pattern Recognition · Computer Science 2023-03-07 Shiwei Liu , Tianlong Chen , Xiaohan Chen , Xuxi Chen , Qiao Xiao , Boqian Wu , Tommi Kärkkäinen , Mykola Pechenizkiy , Decebal Mocanu , Zhangyang Wang

Large kernel convolutions offer a scalable alternative to vision transformers for high-resolution 3D volumetric analysis, yet naively increasing kernel size often leads to optimization instability. Motivated by the spatial bias inherent in…

Computer Vision and Pattern Recognition · Computer Science 2026-02-02 Ho Hin Lee , Quan Liu , Shunxing Bao , Yuankai Huo , Bennett A. Landman

Pillar-based 3D object detection has gained traction in self-driving technology due to its speed and accuracy facilitated by the artificial densification of pillars for GPU-friendly processing. However, dense pillar processing fundamentally…

Computer Vision and Pattern Recognition · Computer Science 2024-08-27 Seongmin Park , Minjae Lee , Junwon Choi , Jungwook Choi

Deep neural networks (DNNs) have heavily relied on traditional computational units like CPUs and GPUs. However, this conventional approach brings significant computational burdens, latency issues, and high power consumption, limiting their…

Computer Vision and Pattern Recognition · Computer Science 2024-05-29 Quan Liu , Brandon T. Swartz , Ivan Kravchenko , Jason G. Valentine , Yuankai Huo

While going deeper has been witnessed to improve the performance of convolutional neural networks (CNN), going smaller for CNN has received increasing attention recently due to its attractiveness for mobile/embedded applications. It remains…

Computer Vision and Pattern Recognition · Computer Science 2017-06-14 Zhe Li , Xiaoyu Wang , Xutao Lv , Tianbao Yang
‹ Prev 1 3 4 5 6 7 10 Next ›