Journal
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
Volume 32, Issue 10, Pages 4514-4528Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TNNLS.2020.3018790
Keywords
Semantics; Visualization; Binary codes; Correlation; Prototypes; Encoding; Optimization; Class encoding; discrete optimization; learning to hash; semantic preserving; similarity search
Categories
Funding
- Guangdong Basic and Applied Basic Research Foundation [2019A1515110475, 2019Bl515120055]
- Shenzhen Fundamental Research Fund [JCYJ20180306172023949]
- Key Project of Shenzhen Municipal Technology Research [JSGG20200103103401723]
- Open Project Fund from Shenzhen Institute of Artificial Intelligence and Robotics for Society
- Medical Biometrics Perception and Analysis Engineering Laboratory, Shenzhen, China
Ask authors/readers for more resources
The proposed inductive structure consistent hashing (ISCH) method effectively coordinates semantic correlations between the visual feature space, the binary class space, and the discrete hashing space.
Semantic-preserving hashing establishes efficient multimedia retrieval by transferring knowledge from original data to hash codes so that the latter can preserve the underlying visual and semantic similarities. However, it becomes a crucial bottleneck: how to effectively bridge the trilateral domain gaps (i.e., the visual, semantic, and hashing spaces) to further improve the retrieval accuracy. In this article, we propose an inductive structure consistent hashing (ISCH) method, which can interactively coordinate the semantic correlations between the visual feature space, the binary class space, and the discrete hashing space. Specifically, an inductive semantic space is formulated by a simple multilayer stacking class-encoder, which transforms the naive class information into flexible semantic embeddings. Meanwhile, we design a semantic dictionary learning model to facilitate the bilateral visual-semantic bridging and guide the class-encoder toward reliable semantics, which could well alleviate the visual-semantic bias problem. In particular, the visual descriptors and respective semantic class representations are regularized with a coinciding alignment module. In order to generate privileged hash codes, we further explore semantic and prototype binary code learning to jointly quantify the semantic and latent visual representations into unified discrete hash codes. Moreover, an efficient optimization algorithm is developed to address the resulting discrete programming problem. Comprehensive experiments conducted on four large-scale data sets, i.e., CIFAR-10, NUSWIDE, ImageNet, and MSCOCO, demonstrate the superiority of our method over the state-of-the-art alternatives against different evaluation protocols.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available