Deep hashing with mixed supervised losses for image search

Dawei Liang, Ke Yan, Wei Zeng, Yaowei Wang, Qingsheng Yuan, Xiuguo Bao, Yonghong Tian*

*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

1 引用 (Scopus)

摘要

Deep convolutional neural networks (DCNN) have revolutionized almost the whole computer vision fields, including learning to hash for image search. Recently, several supervised deep hashing methods are proposed to deal with large-scale image search, where most methods only consider one kind of supervised loss. In this paper, we show that image search performance can be further boosted by combining two kinds of supervised losses, by taking the combination of point-wise and triplet-wise losses as a study case. Two kinds of strategies are proposed to combine the strengths of them. One strategy is that the DCNN is first pre-trained with point-wise loss and then fine-tuned with triplet-wise loss. The other one is that the DCNN is trained jointly with point-wise and triplet-wise losses. We perform extensive experiments on two public benchmark datasets CIFAR-10 and NUS-WIDE. Experimental results demonstrate that the proposed methods outperform the compared methods with single supervised loss.

源语言英语
主期刊名2017 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2017
出版商Institute of Electrical and Electronics Engineers Inc.
507-512
页数6
ISBN(电子版)9781538605608
DOI
出版状态已出版 - 5 9月 2017
已对外发布
活动2017 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2017 - Hong Kong, 香港
期限: 10 7月 201714 7月 2017

出版系列

姓名2017 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2017

会议

会议2017 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2017
国家/地区香港
Hong Kong
时期10/07/1714/07/17

指纹

探究 'Deep hashing with mixed supervised losses for image search' 的科研主题。它们共同构成独一无二的指纹。

引用此

Liang, D., Yan, K., Zeng, W., Wang, Y., Yuan, Q., Bao, X., & Tian, Y. (2017). Deep hashing with mixed supervised losses for image search. 在 2017 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2017 (页码 507-512). 文章 8026273 (2017 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2017). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICMEW.2017.8026273