CVPR 2011 (2011)
June 20, 2011 to June 25, 2011
S. Vijayanarasimhan , Univ. of Texas at Austin, Austin, TX, USA
K. Grauman , Univ. of Texas at Austin, Austin, TX, USA
Active learning and crowdsourcing are promising ways to efficiently build up training sets for object recognition, but thus far techniques are tested in artificially controlled settings. Typically the vision researcher has already determined the dataset's scope, the labels "actively" obtained are in fact already known, and/or the crowd-sourced collection process is iteratively fine-tuned. We present an approach for live learning of object detectors, in which the system autonomously refines its models by actively requesting crowd-sourced annotations on images crawled from the Web. To address the technical issues such a large-scale system entails, we introduce a novel part-based detector amenable to linear classifiers, and show how to identify its most uncertain instances in sub-linear time with a hashing-based solution. We demonstrate the approach with experiments of unprecedented scale and autonomy, and show it successfully improves the state-of-the-art for the most challenging objects in the PASCAL benchmark. In addition, we show our detector competes well with popular nonlinear classifiers that are much more expensive to train.
nonlinear classifiers, large scale live active learning, object detector training, crawled data, crowds, active learning, crowdsourcing, object recognition, artificially controlled settings, vision researcher, crowd sourced image annotations, Web, linear classifiers, hashing based solution, PASCAL benchmark
K. Grauman and S. Vijayanarasimhan, "Large-scale live active learning: Training object detectors with crawled data and crowds," CVPR 2011(CVPR), Providence, RI, 2011, pp. 1449-1456.