Recently active learning has attracted a lot of attention in computer vision field, as it is time and cost consuming to prepare a good set of labeled images for vision data analysis. Most existing active learning approaches employed in computer vision adopt most uncertainty measures as instance selection criteria. Although most uncertainty query selection strategies are very effective in many circumstances, they fail to take information in the large amount of unlabeled instances into account and are prone to querying outliers. In this paper, we present a novel adaptive active learning approach that combines an information density measure and a most uncertainty measure together to select critical instances to label for image classifications. Our experiments on two essential tasks of computer vision, object recognition and scene recognition, demonstrate the efficacy of the proposed approach.

26th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2013
School of Computer Science

Li, X. (Xin), & Guo, Y. (2013). Adaptive active learning for image classification. In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (pp. 859–866). doi:10.1109/CVPR.2013.116