https://scholars.lib.ntu.edu.tw/handle/123456789/632542
標題: | Learning compact binary descriptors with unsupervised deep neural networks | 作者: | Lin K Lu J CHU-SONG CHEN Zhou J. |
公開日期: | 2016 | 卷: | 2016-December | 起(迄)頁: | 1183-1192 | 來源出版物: | Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition | 摘要: | In this paper, we propose a new unsupervised deep learning approach called DeepBit to learn compact binary descriptor for efficient visual object matching. Unlike most existing binary descriptors which were designed with random projections or linear hash functions, we develop a deep neural network to learn binary descriptors in an unsupervised manner. We enforce three criterions on binary codes which are learned at the top layer of our network: 1) minimal loss quantization, 2) evenly distributed codes and 3) uncorrelated bits. Then, we learn the parameters of the networks with a back-propagation technique. Experimental results on three different visual analysis tasks including image matching, image retrieval, and object recognition clearly demonstrate the effectiveness of the proposed approach. © 2016 IEEE. |
URI: | https://www.scopus.com/inward/record.uri?eid=2-s2.0-84986249698&doi=10.1109%2fCVPR.2016.133&partnerID=40&md5=d0d2378dbac9ba5b8c9340b8798812e2 https://scholars.lib.ntu.edu.tw/handle/123456789/632542 |
ISSN: | 10636919 | DOI: | 10.1109/CVPR.2016.133 | SDG/關鍵字: | Backpropagation; Bins; Computer vision; Hash functions; Image matching; Network layers; Object recognition; Deep learning; Deep neural networks; Descriptors; Distributed codes; Linear hash function; Random projections; Visual analysis; Visual objects; Pattern recognition |
顯示於: | 資訊工程學系 |
在 IR 系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。