Title :
Adaptive Active Learning for Image Classification
Author :
Xin Li ; Yuhong Guo
Author_Institution :
Dept. of Comput. & Inf. Sci., Temple Univ., Philadelphia, PA, USA
Abstract :
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.
Keywords :
computer vision; image classification; learning (artificial intelligence); natural scenes; object recognition; query processing; adaptive active learning approach; computer vision field; critical instance selection criteria; image classifications; information density measure; labeled images; object recognition; scene recognition; uncertainty measures; uncertainty query selection strategies; vision data analysis; Covariance matrices; Current measurement; Density measurement; Learning systems; Measurement uncertainty; Training; Uncertainty; active learning; image classification;
Conference_Titel :
Computer Vision and Pattern Recognition (CVPR), 2013 IEEE Conference on
Conference_Location :
Portland, OR
DOI :
10.1109/CVPR.2013.116