Abstract
In recent years, learning-based hashing techniques have proven to be efficient for large-scale image retrieval. However, since most of the hash codes learned by deep hashing methods contain repetitive and correlated information, there are some limitations. In this paper, we propose a Dual Attention Triplet Hashing Network (DATH). DATH is implemented with two-stream ConvNet architecture. Specifically, the first neural network focuses on the spatial semantic relevance, and the second neural network focuses on the channel semantic correlation. These two neural networks are incorporated to create an end-to-end trainable framework. At the same time, in order to make better use of label information, DATH combines triplet likelihood loss and classification loss to optimize the network. Experimental results show that DATH has achieved the state-of-the-art performance on benchmark datasets.
Highlights
Image retrieval is a popular problem of image matching, where the similar images are retrieved from a database with respect to a given query image
In order to solve the above problems, this paper proposes a Dual Attention Triplet Hashing Network (DATH), and extensive experimental results on benchmark datasets show that DATH outperforms the state-of-the-art supervised hashing methods
It is noticed that three deep hashing algorithms learn hash codes through pairwise loss function and AlexNet, so the advantage of DATH lies in the use of attention mechanism and the combination of classification loss and triplet loss
Summary
Image retrieval is a popular problem of image matching, where the similar images are retrieved from a database with respect to a given query image. Because of its small storage space and fast query speed, hashing method is quickly applied to image retrieval. In order to make full use of the label information to learn the hash code, combining the triplet label loss and classification loss is worthy of attention. In the field of deep hash retrieval, we need attention mechanism to enhance the feature representation ability of deep networks, so as to reduce the interference of image useless information on generating hash code. In order to solve the above problems, this paper proposes a Dual Attention Triplet Hashing Network (DATH), and extensive experimental results on benchmark datasets show that DATH outperforms the state-of-the-art supervised hashing methods. The results demonstrate that our method outperforms current state-of-the-art methods for image retrieval, which indicates the effectiveness of the proposed method
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
