Paper Info
Title
Incorporating Manifold Ranking with Active Learning in Relevance Feedback for Image Retrieval
Abstract
Combining manifold ranking with active learning (MRAL for short) is one popular and successful technique for relevance feedback in content-based image retrieval (CBIR). Despite the success, conventional MRAL has two main drawbacks. First, the performance of manifold ranking is very sensitive to the scale parameter used for calculating the Laplacian matrix. Second, conventional MRAL does not take into account the redundancy among examples and thus could select multiple examples that are similar to each other. In this work, a novel MRAL framework is presented to address the drawbacks. Concretely, we first propose a self-tuning manifold ranking algorithm that can adaptively calculate the Laplacian matrix via a local scaling mechanism, and then develop a hybrid active learning algorithm by integrating three well-known selective sampling criteria, which is able to effectively and efficiently identify the most informative and diversified examples for the user to label. Experiments on 10,000 Corel images show that the proposed method is significantly more effective than some existing approaches.
Year
DOI
Venue
2012
10.1109/PDCAT.2012.82
PDCAT
Keywords
DocType
ISBN
laplacian matrix,self-tuning manifold ranking algorithm,laplace equations,learning (artificial intelligence),local scaling mechanism,hybrid active learning algorithm,diversified example,mral,incorporating manifold ranking,active learning,content-based image retrieval,image retrieval,cbir,relevance feedback,manifold ranking,corel image,content-based retrieval,novel mral framework,conventional mral,manifold ranking with active learning,learning artificial intelligence
Conference
978-0-7695-4879-1
Citations 
PageRank 
References 
2
0.37
20
Authors
4
Name
Order
Citations
PageRank
Jun Wu112515.66
Yidong Li215143.42
Yingpeng Sang3219.05
Hong Shen449952.98