In this paper, we have proposed a novel framework to achieve more effective classifier training by using unlabeled samples. By integrating concept hierarchy for semantic image concept organization, a hierarchical mixture model is proposed to enable multi-level image concept modeling and hierarchical classifier training. To effectively learn the base-level classifiers for the atomic image concepts at the first level of the concept hierarchy, we have proposed a novel adaptive EM algorithm to achieve more effective classifier training with higher prediction accuracy. To effectively learn the classifiers for the higher-level semantic image concepts, we have also proposed a novel technique for classifier combining by using hierarchical mixture model. The experimental results on two large-scale image databases are also provided.
Learning the semantics of images by using unlabeled samples
01.01.2005
449153 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
MINING UNLABELED IMAGES WITH VISION AND LANGUAGE MODELS FOR IMPROVING OBJECT DETECTION
Europäisches Patentamt | 2023
|REPRESENTATION LEARNING FOR OBJECT DETECTION FROM UNLABELED POINT CLOUD SEQUENCES
Europäisches Patentamt | 2024
|Learning common behaviors from large sets of unlabeled temporal series
British Library Online Contents | 2012
|British Library Conference Proceedings | 2003
|