Name
Abstract | ||
|---|---|---|
Hashing methods play an important role in large scale image retrieval. Traditional hashing methods use hand-crafted features to learn hash functions, which can not capture the high level semantic information. Deep hashing algorithms use deep neural networks to learn feature representation and hash functions simultaneously. Most of these algorithms exploit supervised information to train the deep network. However, supervised information is expensive to obtain. In this paper, we propose a pseudo label based unsupervised deep discriminative hashing algorithm. First, we cluster images via K-means and the cluster labels are treated as pseudo labels. Then we train a deep hashing network with pseudo labels by minimizing the classification loss and quantization loss. Experiments on two datasets demonstrate that our unsupervised deep discriminative hashing method outperforms the state-of-art unsupervised hashing methods.
|
Year | DOI | Venue |
|---|---|---|
2017 | 10.1145/3123266.3123403 | MM '17: ACM Multimedia Conference
Mountain View
California
USA
October, 2017 |
Keywords | Field | DocType |
Deep Hashing, Unsupervised hashing, Pseudo Labels | Locality-sensitive hashing,Pattern recognition,Computer science,Feature hashing,Image retrieval,Semantic information,Hash function,Artificial intelligence,Quantization (signal processing),Discriminative model,Machine learning,Deep neural networks | Conference |
ISBN | Citations | PageRank |
978-1-4503-4906-2 | 4 | 0.39 |
References | Authors | |
10 | 5 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| qinghao hu | 1 | 163 | 8.86 |
| Jiaxiang Wu | 2 | 191 | 10.12 |
| Jian Cheng | 3 | 1327 | 115.72 |
| Lifang Wu | 4 | 13 | 4.52 |
| Hanqing Lu | 5 | 4620 | 291.38 |