Back to Search
Start Over
Deep Position-Aware Hashing for Semantic Continuous Image Retrieval
- Source :
- WACV
- Publication Year :
- 2020
- Publisher :
- IEEE, 2020.
-
Abstract
- Preserving the semantic similarity is one of the most important goals of hashing. Most existing deep hashing methods employ pairs or triplets of samples in training stage, which only consider the semantic similarity within a minibatch and depict the local positional relationship in Hamming space, leading to intermittent semantic similarity preservation. In this paper, we propose Deep Position-Aware Hashing (DPAH) to ensure continuous semantic similarity in Hamming space by modeling global positional relationship. Specifically, we introduce a set of learnable class centers as the global proxies to represent the global information and generate discriminative binary codes by constraining the distance between data points and class centers. In addition, in order to reduce the information loss caused by relaxing the binary codes to real-values in optimization, we propose kurtosis loss (KT loss) to handle the distribution of real-valued features before thresholding to be double-peak, and then enable the real-valued features to be more binarylike. Comprehensive experiments on three datasets show that our DPAH outperforms state-of-the-art methods.
- Subjects :
- Computer science
business.industry
Hash function
Pattern recognition
02 engineering and technology
010501 environmental sciences
01 natural sciences
Thresholding
Set (abstract data type)
Discriminative model
Semantic similarity
0202 electrical engineering, electronic engineering, information engineering
020201 artificial intelligence & image processing
Binary code
Artificial intelligence
Hamming space
business
Image retrieval
0105 earth and related environmental sciences
Subjects
Details
- Database :
- OpenAIRE
- Journal :
- 2020 IEEE Winter Conference on Applications of Computer Vision (WACV)
- Accession number :
- edsair.doi...........2309047d300653ed05ca41645788945d