Active learning combining uncertainty and diversity for multi-class image classification

• Published in: IET computer vision 2015-06, Vol.9 (3), p.400-407
• Main Authors: Gu, Yingjie, Jin, Zhong, Chiu, Steve C
• Format: Article
• Language: English
• Subjects: active learning algorithm; Algorithms; binary SVM classiflers; Computer vision; dynamic programming; dynamic programming method; Gaussian kernel; Image classification; Labelling; Learning; learning (artificial intelligence); multiclass image classification; pattern recognition applications; Strategy; support vector machine; Support vector machines; Uncertainty; unlabelled data
• ISSN: 1751-9632; 1751-9640; 1751-9640
• DOI: 10.1049/iet-cvi.2014.0140

In computer vision and pattern recognition applications, there are usually a vast number of unlabelled data whereas the labelled data are very limited. Active learning is a kind of method that selects the most representative or informative examples for labelling and training; thus, the best prediction accuracy can be achieved. A novel active learning algorithm is proposed here based on one-versus-one strategy support vector machine (SVM) to solve multi-class image classification. A new uncertainty measure is proposed based on some binary SVM classifiers and some of the most uncertain examples are selected from SVM output. To ensure that the selected examples are diverse from each other, Gaussian kernel is adopted to measure the similarity between any two examples. From the previous selected examples, a batch of diverse and uncertain examples are selected by the dynamic programming method for labelling. The experimental results on two datasets demonstrate the effectiveness of the proposed algorithm.