Exploiting Privileged Information from Web Data for Image Categorization

Relevant and irrelevant web images collected by tag-based image retrieval have been employed as loosely labeled training data for learning SVM classifiers for image categorization by only using the visual features. In this work, we propose a new image categorization method by incorporating the textual features extracted from the surrounding textual descriptions (tags, captions, categories, etc.) as privileged information and simultaneously coping with noise in the loose labels of training web images. When the training and test samples come from different datasets, our proposed method can be further extended to reduce the data distribution mismatch by adding a regularizer based on the Maximum Mean Discrepancy (MMD) criterion. Our comprehensive experiments on three benchmark datasets demonstrate the effectiveness of our proposed methods for image categorization and image retrieval by exploiting privileged information from web data.