Object detection based deep unsupervised hashing

Rong Cheng Tu, Xian Ling Mao*, Bo Si Feng, Shu Ying Yu

*此作品的通讯作者

科研成果: 书/报告/会议事项章节会议稿件同行评审

7 引用 (Scopus)

摘要

Recently, similarity-preserving hashing methods have been extensively studied for large-scale image retrieval. Compared with unsupervised hashing, supervised hashing methods for labeled data have usually better performance by utilizing semantic label information. Intuitively, for unlabeled data, it will improve the performance of unsupervised hashing methods if we can first mine some supervised semantic'label information' from unlabeled data and then incorporate the'label information' into the training process. Thus, in this paper, we propose a novel Object Detection based Deep Unsupervised Hashing method (ODDUH). Specifically, a pre-trained object detection model is utilized to mining supervised'label information', which is used to guide the learning process to generate high-quality hash codes. Extensive experiments on two public datasets demonstrate that the proposed method outperforms the state-of-the-art unsupervised hashing methods in the image retrieval task.

源语言英语
主期刊名Proceedings of the 28th International Joint Conference on Artificial Intelligence, IJCAI 2019
编辑Sarit Kraus
出版商International Joint Conferences on Artificial Intelligence
3606-3612
页数7
ISBN(电子版)9780999241141
DOI
出版状态已出版 - 2019
活动28th International Joint Conference on Artificial Intelligence, IJCAI 2019 - Macao, 中国
期限: 10 8月 201916 8月 2019

出版系列

姓名IJCAI International Joint Conference on Artificial Intelligence
2019-August
ISSN(印刷版)1045-0823

会议

会议28th International Joint Conference on Artificial Intelligence, IJCAI 2019
国家/地区中国
Macao
时期10/08/1916/08/19

指纹

探究 'Object detection based deep unsupervised hashing' 的科研主题。它们共同构成独一无二的指纹。

引用此