Scalable deep asymmetric hashing via unequal-dimensional embeddings for image similarity search
| Autor: | Lei Zhu, Wenti Huang, Jun Long, Zhifang Liao, Zhan Yang, Osolo Ian Raymond |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
0209 industrial biotechnology
Theoretical computer science Computer science Cognitive Neuroscience Nearest neighbor search Hash function 02 engineering and technology Computer Science Applications Image (mathematics) Reduction (complexity) 020901 industrial engineering & automation Artificial Intelligence Scalability 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing Binary code Image retrieval |
| Zdroj: | Neurocomputing. 412:262-275 |
| ISSN: | 0925-2312 |
| DOI: | 10.1016/j.neucom.2020.06.036 |
| Popis: | In recent years, Hashing has become a popular technique used to support large-scale image retrieval, due to its significantly reduced storage, high search speed and capability of mapping high dimensional original features into compact similarity-preserving binary codes. Although effectiveness achieved, most existing hashing methods are still some limitations, including: (1) Many supervised hashing methods only transform the label information into pairwise similarities to guide the hash code learning process, which will lead to the loss of rich semantic information between image pairs. (2) Some pioneer hashing methods use a relaxation-based strategy to solve discrete problems, resulting in a large quantization error. (3) Some supervised hashing methods handle the hashing learning procedure based on an asymmetric learning manner, and although this partially solves the problems of low efficiency and accuracy of symmetric learning strategy, they are all based on the embeddings of equal dimension, which leads to the reduction in the models representation ability and an increase in potential noise. To overcome the above limitations, in this paper, we propose a novel yet simple but effective hashing method, named Scalable Deep Asymmetric Hashing (SDAH). Specifically, SDAH is an end-to-end deep hashing method based on a fast iterative optimization strategy, which utilizes two real-valued embeddings of unequal dimensions, i.e., real-valued embeddings of images and labels, to flexibly perform asymmetric similarity computation. It can circumvent the use of the large pairwise similarity matrix by introducing an intermediate label matrix term which results in a remarkable reduction in the memory space cost. By doing this, the learned hash codes are more semantically informative for image retrieval tasks. Experimental results on several benchmark datasets highlight the superiority of SDAH in comparison with many state-of-the-art hashing methods. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full Text from ScienceDirect