Multipath Convolutional-Recursive Neural Networks for Object Recognition

摘要：

　　Extracting good representations from images is essential for many computer vision tasks.While progress in deep learning shows the importance of learning hierarchical features, it is also important to learn features through multiple paths.This paper presents Multipath Convolutional-Recursive Neural Networks(M-CRNNs), a novel scheme which aims to learn image features from multiple paths using models based on combination of convolutional and recursive neural networks (CNNs and RNNs).CNNs learn low-level features, and RNNs, whose inputs are the outputs of the CNNs, learn the efficient high-level features.The final features of an image are the combination of the features from all the paths.The result shows that the features learned from M-CRNNs are a highly discriminative image representation that increases the precision in object recognition.

关键词： Multiple paths convolutional neural networks recursive neural networks classification

作者: Xiangyang Li Shuqiang Jiang Xinhang Song Luis Herranz Zhiping Shi

作者单位: Capital Normal University, College of Information Engineering, Beijing, China;Key Lab of Intelligent Key Lab of Intelligent Information Processing, Institute of Computing Tech., Beijing, China Capital Normal University, College of Information Engineering, Beijing, China

会议类型: 国际会议

会议名称: 8th International Conference on Intelligent Information Processing(2014年IFIP智能信息处理国际会议)

会议地点: 杭州

会议语种:英文

页码: 269-277

在线出版日期: 2014-10-01（万方平台首次上网日期，不代表论文的发表时间）