Adaptive Active Learning for Image Classification
Authors:
- Xin LiXLXin Li
- Yuhong GuoYGYuhong Guo
- 1 June 2013
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 10636919,p. 859-866
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
This publication has 22 references indexed in Scilit:
- Large-scale live active learning: Training object detectors with crawled data and crowds2011
- Dynamic batch mode active learning2011
- An analysis of active learning strategies for sequence labeling tasks2008
- Active Image Labeling and Its Application to Facial Action Labeling2008
- Learning generative visual models from few training examples: An incremental Bayesian approach tested on 101 object categoriesComputer Vision and Image Understanding, 2007
- Extreme video retrieval2006
- Active learning using pre-clustering2004
- An active learning framework for content-based information retrievalIEEE Transactions on Multimedia, 2002
- Modeling the Shape of the Scene: A Holistic Representation of the Spatial EnvelopeInternational Journal of Computer Vision, 2001
- A Sequential Algorithm for Training Text Classifiers1994