Irregular Convolutional Neural Networks

CASIA OpenIR > 智能感知与计算研究中心

	Irregular Convolutional Neural Networks
	Ma JB(马佳彬); Wang W(王威); Wang L(王亮)
	2017-11
会议名称	Asian Conference on Pattern Recognition (ACPR)
会议日期	November 26-29 2017
会议地点	Nanjing, China
摘要	Convolutional kernels are basic and vital components of deep Convolutional Neural Networks (CNN). In this paper, we equip convolutional kernels with shape attributes to generate the deep Irregular Convolutional Neural Networks (ICNN). Compared to traditional CNN applying regular convolutional kernels like 3 × 3, our approach trains irregular kernel shapes to better fit the geometric variations of input features. In other words, shapes are learnable parameters in addition to weights. The kernel shapes and weights are learned simultaneously during end-to-end training with the standard back-propagation algorithm. Experiments for semantic segmentation are implemented to validate the effectiveness of our proposed ICNN
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/173211/20658
专题	智能感知与计算研究中心
作者单位	中国科学院自动化研究所
第一作者单位	中国科学院自动化研究所
推荐引用方式 GB/T 7714	Ma JB,Wang W,Wang L. Irregular Convolutional Neural Networks[C],2017.