Name
Abstract | ||
|---|---|---|
Recent studies show that hashing technology can achieve efficient similarity searching and many works have been done on supervised deep hash learning. However, under unsupervised scenarios, there are several issues to be solved when learning hashing codes based on visual features for image retrieval and clustering. In this article, we propose a simple but effective Unsupervised Deep K-means Hashing (UDKH) method to simultaneously alleviate the problems of image retrieval and clustering within a single learning framework. UDKH progressively improves the quality of cluster labels and binary hash codes by minimizing pair-wise supervision loss and optimizing the binary K-means to generate discriminative hash codes under the supervision of the learned cluster labels for effective image retrieval. Since the learned hash codes are discriminative, UDKH also improves the image clustering accuracy. Experiments on test datasets demonstrate its effectiveness for image retrieval and clustering. |
Year | DOI | Venue |
|---|---|---|
2021 | 10.1109/TCSVT.2020.3035775 | IEEE Transactions on Circuits and Systems for Video Technology |
Keywords | DocType | Volume |
Image retrieval,unsupervised hashing,clustering,deep learning | Journal | 31 |
Issue | ISSN | Citations |
8 | 1051-8215 | 1 |
PageRank | References | Authors |
0.35 | 29 | 5 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Xiao Dong | 1 | 24 | 3.06 |
| Li Liu | 2 | 169 | 50.09 |
| Lei Zhu | 3 | 854 | 51.69 |
| Zhiyong Cheng | 4 | 546 | 32.55 |
| Huaxiang Zhang | 5 | 436 | 56.32 |