Back to Search
Start Over
DistillHash: Unsupervised Deep Hashing by Distilling Data Pairs
- Source :
- CVPR
- Publication Year :
- 2019
- Publisher :
- IEEE, 2019.
-
Abstract
- Due to the high storage and search efficiency, hashing has become prevalent for large-scale similarity search. Particularly, deep hashing methods have greatly improved the search performance under supervised scenarios. In contrast, unsupervised deep hashing models can hardly achieve satisfactory performance due to the lack of reliable supervisory similarity signals. To address this issue, we propose a novel deep unsupervised hashing model, dubbed DistillHash, which can learn a distilled data set consisted of data pairs, which have confidence similarity signals. Specifically, we investigate the relationship between the initial noisy similarity signals learned from local structures and the semantic similarity labels assigned by a Bayes optimal classifier. We show that under a mild assumption, some data pairs, of which labels are consistent with those assigned by the Bayes optimal classifier, can be potentially distilled. Inspired by this fact, we design a simple yet effective strategy to distill data pairs automatically and further adopt a Bayesian learning framework to learn hash functions from the distilled data set. Extensive experimental results on three widely used benchmark datasets show that the proposed DistillHash consistently accomplishes the state-of-the-art search performance.
- Subjects :
- FOS: Computer and information sciences
Computer science
business.industry
Computer Vision and Pattern Recognition (cs.CV)
Nearest neighbor search
Hash function
Computer Science - Computer Vision and Pattern Recognition
Pattern recognition
02 engineering and technology
010501 environmental sciences
01 natural sciences
Data set
Naive Bayes classifier
Semantic similarity
Similarity (network science)
0202 electrical engineering, electronic engineering, information engineering
Unsupervised learning
020201 artificial intelligence & image processing
Artificial intelligence
business
0105 earth and related environmental sciences
Subjects
Details
- Database :
- OpenAIRE
- Journal :
- 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
- Accession number :
- edsair.doi.dedup.....e9128c8723263bf40a52e5f088dbf134