https://scholars.lib.ntu.edu.tw/handle/123456789/581340
標題: | Supervised Learning of Semantics-Preserving Hash via Deep Convolutional Neural Networks | 作者: | Yang H.-F Lin K CHU-SONG CHEN |
關鍵字: | Binary codes; Bins; Classification (of information); Codes (symbols); Convolution; Deep learning; Hash functions; Image retrieval; Neural networks; Semantic Web; Semantics; Classification errors; Classification performance; Convolutional neural network; Image representations; Large-scale datasets; Objective functions; State-of-the-art approach; supervised hashing; Deep neural networks | 公開日期: | 2018 | 卷: | 40 | 期: | 2 | 起(迄)頁: | 437-451 | 來源出版物: | IEEE Transactions on Pattern Analysis and Machine Intelligence | 摘要: | This paper presents a simple yet effective supervised deep hash approach that constructs binary hash codes from labeled data for large-scale image search. We assume that the semantic labels are governed by several latent attributes with each attribute on or off, and classification relies on these attributes. Based on this assumption, our approach, dubbed supervised semantics-preserving deep hashing (SSDH), constructs hash functions as a latent layer in a deep network and the binary codes are learned by minimizing an objective function defined over classification error and other desirable hash codes properties. With this design, SSDH has a nice characteristic that classification and retrieval are unified in a single learning model. Moreover, SSDH performs joint learning of image representations, hash codes, and classification in a point-wised manner, and thus is scalable to large-scale datasets. SSDH is simple and can be realized by a slight enhancement of an existing deep architecture for classification; yet it is effective and outperforms other hashing approaches on several benchmarks and large datasets. Compared with state-of-the-art approaches, SSDH achieves higher retrieval accuracy, while the classification performance is not sacrificed. ? 2017 IEEE. |
URI: | https://www.scopus.com/inward/record.uri?eid=2-s2.0-85040643919&doi=10.1109%2fTPAMI.2017.2666812&partnerID=40&md5=d496ff63ee56a38c1f8b18b9f205d053 https://scholars.lib.ntu.edu.tw/handle/123456789/581340 |
ISSN: | 01628828 | DOI: | 10.1109/TPAMI.2017.2666812 |
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。