Deep Supervised Hashing with Nonlinear Projections
Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence. Main track. Pages 2786-2792.
https://doi.org/10.24963/ijcai.2017/388
Keywords
- Machine Learning: Machine Learning
- Multidisciplinary Topics and Applications: Multidisciplinary Topics and Applications
- Machine Learning: Deep Learning
Abstract
Hashing has attracted broad research interests in large scale image retrieval due to its high search speed and efficient storage. Recently, many deep hashing methods have been proposed to perform simultaneous nonlinear feature learning and hash projection learning, which have shown superior performance compared to hand-crafted feature based hashing methods. Nonlinear projection functions have shown their advantages over the linear ones due to their powerful generalization capabilities. To improve the performance of deep hashing methods by generalizing projection functions, we propose the idea of implementing a pure nonlinear deep hashing network architecture. By consolidating the above idea, this paper presents a Deep Supervised Hashing architecture with Nonlinear Projections (DSHNP). In particular, soft decision trees are adopted as the nonlinear projection functions, since they can generate differentiable nonlinear outputs and can be trained with deep neural networks in an end-to-end way. Moreover, to make the hash codes as independent as possible, we design two regularizers imposed on the parameter matrices of the leaves in the soft decision trees. Extensive evaluations on two benchmark image datasets show that the proposed DSHNP outperforms several state-of-the-art hashing methods.
Full text extracted automatically from the PDF; figures, tables and equations may differ. The PDF is the version of record.
-
-
-



| | | | ||||||
|---|---|---|---|---|---|---|---|---|
| | | | | | | | | |
| | | | | | | | | |
| | | | | | | | | |
| | | | | | | | | |
| | | | | | | | | |
| | | | | | | | | |
| | | | | | | | | |
| | | | | | | | | |
| | | | | | | | | |
| | | | | | | | | |
| | | | | | | | | |
| | | | | | | | | |
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
@inproceedings{ijcai2017p388,
title = {Deep Supervised Hashing with Nonlinear Projections},
author = {Su, Sen and Chen, Gang and Cheng, Xiang and Bi, Rong},
booktitle = {Proceedings of the Twenty-Sixth International Joint Conference on
Artificial Intelligence, {IJCAI-17}},
publisher = {International Joint Conferences on Artificial Intelligence Organization},
editor = {Carles Sierra},
pages = {2786--2792},
year = {2017},
month = {8},
note = {Main track},
doi = {10.24963/ijcai.2017/388},
url = {https://doi.org/10.24963/ijcai.2017/388},
}
TY - CPAPER TI - Deep Supervised Hashing with Nonlinear Projections AU - Su, Sen AU - Chen, Gang AU - Cheng, Xiang AU - Bi, Rong T2 - Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence, IJCAI-17 PB - International Joint Conferences on Artificial Intelligence Organization PY - 2017 SP - 2786 EP - 2792 DO - 10.24963/ijcai.2017/388 UR - https://doi.org/10.24963/ijcai.2017/388 ER -Copied
Machine-readable versions of this paper, for tools and AI agents: