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
2018-08
会议名称International Conference on Pattern Recognition (ICPR)
会议日期August 20-24 2018
会议地点Beijing, China
摘要In 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.
URL查看原文
收录类别EI
语种英语
文献类型会议论文
条目标识符http://ir.ia.ac.cn/handle/173211/20885
专题智能感知与计算研究中心
作者单位1.中国科学院自动化研究所
2.中国科学院大学
推荐引用方式
GB/T 7714
Ma JB,Guo WY,Wang W,et al. RotateConv: Making Asymmetric Convolutional Kernels Rotatable[C],2018.
条目包含的文件 下载所有文件
文件名称/大小 文献类型 版本类型 开放类型 使用许可
bare_conf.pdf(831KB)会议论文 开放获取CC BY-NC-SA浏览 下载
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Ma JB(马佳彬)]的文章
[Guo WY(郭韦煜)]的文章
[Wang W(王威)]的文章
百度学术
百度学术中相似的文章
[Ma JB(马佳彬)]的文章
[Guo WY(郭韦煜)]的文章
[Wang W(王威)]的文章
必应学术
必应学术中相似的文章
[Ma JB(马佳彬)]的文章
[Guo WY(郭韦煜)]的文章
[Wang W(王威)]的文章
相关权益政策
暂无数据
收藏/分享
文件名: bare_conf.pdf
格式: Adobe PDF
所有评论 (0)
暂无评论
 

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。