Sparse coding and classifier ensemble based multi-instance learning for image categorization

In this paper, we propose a novel method based on sparse coding and classifier ensemble for tackling image categorization problem under the framework of multi-instance learning (MIL). Specifically, a dictionary is learned from the instances of all the training bags. Each instance of a bag is represented as a sparse linear combination of all basis vectors in the dictionary, and then the bag is also represented one feature vector which is achieved via sparse representations of all instances within the bag. Thus, the MIL problem is converted to a single-instance learning problem that can be solved by well-know single-instance learning methods, such as support vector machines (SVMs). Two strategies are used to improve classification performance: first, the component classifiers are obtained by repeatedly using the above method with dictionaries of different sizes; second, the result of classifier ensemble is used for prediction. Experimental results on the COREL data sets demonstrate the superiority of the proposed method in terms of classification accuracy as compared with state-of-the-art MIL methods.