Uncertainty-Aware and Multigranularity Consistent Constrained Model for Semi-Supervised Hashing
- 12 May 2022
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 32 (10) , 6914-6926
Abstract
Recently, deep semi-supervised hashing methods have attracted increasing attention, which can significantly improve retrieval performance by leveraging abundant unlabeled data. These methods usually generate surrogate supervision signals to learn with unlabeled data, such as neighborhood information and augmentation invariant requirements. However, an essential issue of these methods is that the supervised signals are not always reliable, which may damage the performance. In this paper, we propose a novel Uncertainty-Aware and Multi-Granularity Consistent Constrained Semi-Supervised Hashing (UMCSH) method to alleviate the negative effects of noisy supervised signals and enlarge the inter-class distance. Specifically, our UMCSH mainly consists of an Uncertainty-Aware Instance-Level Consistency (UAILC) model and a Cluster-Based Class-Level Consistency (CBCLC) model. UAILC introduces an uncertainty estimation method to select reliable supervised signals to extract discriminative features for each unlabeled data. CBCLC establishes connections between labeled data and unlabeled data by encouraging each unlabeled sample to be close to the hash center (calculated with the labeled data) according to its pseudo-label. Extensive experimental results demonstrate the superior performance of our proposed approach compared with several state-of-the-art semi-supervised hashing methods.Keywords
Funding Information
- National Natural Science Foundation of China (62006221, 62106258)
This publication has 50 references indexed in Scilit:
- Semi-supervised Hashing with Semantic Confidence for Large Scale Visual Search2015
- Simultaneous feature learning and hash coding with deep neural networks2015
- Supervised Discrete Hashing2015
- Scalable Nearest Neighbor Algorithms for High Dimensional DataIEEE Transactions on Pattern Analysis and Machine Intelligence, 2014
- Complementary hashing for approximate nearest neighbor search2011
- A balanced semi-supervised hashing method for CBIR2011
- NUS-WIDE2009
- Semi-Supervised Learning (Chapelle, O. et al., Eds.; 2006) [Book reviews]IEEE Transactions on Neural Networks, 2009
- Near-optimal hashing algorithms for approximate nearest neighbor in high dimensionsCommunications of the ACM, 2008
- When Is “Nearest Neighbor” Meaningful?1999