Angular Deep Supervised Hashing for Image Retrieval
Research output: Journal Publications and Reviews › RGC 21 - Publication in refereed journal › peer-review
Author(s)
Related Research Unit(s)
Detail(s)
Original language | English |
---|---|
Article number | 8825992 |
Pages (from-to) | 127521-127532 |
Journal / Publication | IEEE Access |
Volume | 7 |
Online published | 5 Sept 2019 |
Publication status | Published - 2019 |
Link(s)
DOI | DOI |
---|---|
Attachment(s) | Documents
Publisher's Copyright Statement
|
Link to Scopus | https://www.scopus.com/record/display.uri?eid=2-s2.0-85078320236&origin=recordpage |
Permanent Link | https://scholars.cityu.edu.hk/en/publications/publication(ec6c032e-6f66-4a87-b4ba-8673f9b1b7f2).html |
Abstract
Deep learning based image hashing methods learn hash codes by using powerful feature extractors and nonlinear transformations to achieve highly efficient image retrieval. For most end-to-end deep hashing methods, the supervised learning process relies on pair-wise or triplet-wise information to provide an internal relationship of similarity data. However, the use of pair-wise and triplet loss function is limited not only by expensive training costs but also by quantization errors. In this paper, we propose a novel semantic learning based hashing method for image retrieval to optimize the deep features structure in the hash space from a perspective of angular view. Specifically, we proposed an angular hashing loss function that explicitly improve intra-class compactness and inter-class separability between features in hash space. Geometrically, angular hashing loss can be regarded as imposing hash constraints on hypersphere manifold. In order to solve the training problem on the multi-label case, we further designed a dynamic Softmax training strategy that can directly train the network using gradient descent method. Extensive experiments on two well-known datasets of CIFAR-10 and NUS-WIDE demonstrate that the proposed Angular Deep Supervised Hashing (ADSH) method can generate high-quality and compact binary codes, which can achieve state-of-the-art performance as compared with conventional image hashing and deep learning-based hashing methods.
Research Area(s)
- A-Softmax, convolutional neural network, Image retrieval, neural network, quantization, Softmax loss, supervised learning-based hashing
Citation Format(s)
Angular Deep Supervised Hashing for Image Retrieval. / ZHOU, Chang; PO, Lai-Man; YUEN, Wilson Y. F. et al.
In: IEEE Access, Vol. 7, 8825992, 2019, p. 127521-127532.
In: IEEE Access, Vol. 7, 8825992, 2019, p. 127521-127532.
Research output: Journal Publications and Reviews › RGC 21 - Publication in refereed journal › peer-review
Download Statistics
No data available