Paper Info
Title
Employing Hierarchical Clustering and Reinforcement Learning for Attribute-Based Zero-Shot Classification.
Abstract
Zero-shot classification (ZSC) is a hot topic of computer vision. Because the training labels are totally different from the testing labels, ZSC cannot be dealt with by classical classifiers. Attribute-based classifier is a dominant solution for ZSC. It employs attribute annotations to bridge training labels and testing labels, making it able to realize ZSC. Classical attribute-based classifiers treat different attributes equally. However, the attributes contribute to classification unequally. In this paper, a novel attribute-based classifier for ZSC named HCRL is proposed. HCRL utilizes hierarchical clustering to obtain a hierarchy from the attribute annotations. Then the attribute annotations are decomposed into hierarchical rules which contain only a few attributes. The discriminative abilities of the rules reflect the significances of attributes to classification, but there are no training samples for evaluating the rules. The discriminative abilities are determined by reinforcement learning during the testing and the most discriminative rules are picked out for classification. Experiments conducted on 2 popular datasets for ZSC show the competitiveness of HCRL.
Year
DOI
Venue
2017
10.1007/978-3-319-69179-4_25
ADVANCED DATA MINING AND APPLICATIONS, ADMA 2017
Keywords
Field
DocType
Reinforcement learning,Image classification,Attribute,Zero-Shot classification,Hierarchical clustering
Hierarchical clustering,Pattern recognition,Computer science,Consensus clustering,Artificial intelligence,Conceptual clustering,Contextual image classification,Cluster analysis,Brown clustering,Discriminative model,Machine learning,Learning classifier system
Conference
Volume
ISSN
Citations 
10604
0302-9743
0
PageRank 
References 
Authors
0.34
12
4
Name
Order
Citations
PageRank
Bin Liu1103.53
Li Yao22110.45
Junfeng Wu352.77
Xiaosheng Feng400.34