CASIA OpenIR  > 智能感知与计算研究中心
RotateConv: Making Asymmetric Convolutional Kernels Rotatable
Ma JB(马佳彬)1,2; Guo WY(郭韦煜)1; Wang W(王威)1; Wang L(王亮)1
Conference NameInternational Conference on Pattern Recognition (ICPR)
Conference DateAugust 20-24 2018
Conference PlaceBeijing, China
AbstractIn deep Convolutional Neural Networks(CNN), the design of kernel shapes influences a lot on the model size and performance. In this work, our proposed method, RotateConv, applies a novel kernel shape to massively reduce the number of parameters while maintaining considerable performance. The new shape is extremely simple as a line segment one, and we equip it with the rotatable ability which aims to learn diverse features with respect to different angles. The kernel weights and angles are learned simultaneously during end-to-end training via the standard back-propagation algorithm. There are two variants of RotateConv that only have 2 and 4 parameters respectively depending on whether using weight sharing, which are much compressed than the normal 3x3 kernel with 9 parameters. In experiments, we validate our RotateConv with two classical models, ResNet and DenseNet, on four image classification benchmark datasets, namely MNIST, CIFAR10, CIFAR100 and SVHN.
Indexed ByEI
Document Type会议论文
Recommended Citation
GB/T 7714
Ma JB,Guo WY,Wang W,et al. RotateConv: Making Asymmetric Convolutional Kernels Rotatable[C],2018.
Files in This Item: Download All
File Name/Size DocType Version Access License
bare_conf.pdf(831KB)会议论文 开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Ma JB(马佳彬)]'s Articles
[Guo WY(郭韦煜)]'s Articles
[Wang W(王威)]'s Articles
Baidu academic
Similar articles in Baidu academic
[Ma JB(马佳彬)]'s Articles
[Guo WY(郭韦煜)]'s Articles
[Wang W(王威)]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Ma JB(马佳彬)]'s Articles
[Guo WY(郭韦煜)]'s Articles
[Wang W(王威)]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: bare_conf.pdf
Format: Adobe PDF
All comments (0)
No comment.

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.