Towards self-exploring discriminating features for visual learning

Many visual learning tasks are usually confronted by some common difficulties. One of them is the lack of supervised information, due to the fact that labeling could be tedious, expensive or even impossible. Another difficulty is the high dimensionality of the visual data. Fortunately, these difficulties could be alleviated by using a hybrid of labeled and unlabeled training data for learning. Since the unlabeled data characterize the joint probability across different features, they could be used to boost weak classifiers by exploring discriminating features in a self-supervised fashion. This paper proposes a novel method, the Discriminant-EM (D-EM) algorithm, which attacks these difficulties by integrating discriminant analysis with the EM framework in this hybrid formulation. Both linear and nonlinear methods are investigated in this paper. Based on kernel multiple discriminant analysis, the nonlinear D-EM provides better ability to simplify the probabilistic structures of data distributions in a discrimination space. We also propose a novel data-sampling scheme for efficient learning of kernel discriminants. Our experimental results show that D-EM outperforms a variety of supervised and semi-supervised learning algorithms for many visual learning tasks, such as content-based image retrieval, invariant object recognition, and nonstationary color tracking. The proposed approach could be easily applied for many other learning tasks.