User-Centric Learning and Evaluation of Interactive Segmentation Systems
International Journal of Computer Vision
Constrained semi-supervised learning using attributes and comparative attributes
ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part III
To track or to detect? an ensemble framework for optimal selection
ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part V
Web-enhanced object category learning for domestic robots
Intelligent Service Robotics
Using tagged images of low visual ambiguity to boost the learning efficiency of object detectors
Proceedings of the 21st ACM international conference on Multimedia
Feedback-driven multiclass active learning for data streams
Proceedings of the 22nd ACM international conference on Conference on information & knowledge management
Computer Vision and Image Understanding
| Hi-index | 0.00 |
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.