Solving the multiple instance problem with axis-parallel rectangles
Artificial Intelligence
Learning cost-sensitive active classifiers
Artificial Intelligence
Unsupervised Learning of Models for Recognition
ECCV '00 Proceedings of the 6th European Conference on Computer Vision-Part I
ICML '02 Proceedings of the Nineteenth International Conference on Machine Learning
Multiple-Instance Learning for Natural Scene Classification
ICML '98 Proceedings of the Fifteenth International Conference on Machine Learning
Automatically Labeling Video Data Using Multi-class Active Learning
ICCV '03 Proceedings of the Ninth IEEE International Conference on Computer Vision - Volume 2
A Bayesian Approach to Unsupervised One-Shot Learning of Object Categories
ICCV '03 Proceedings of the Ninth IEEE International Conference on Computer Vision - Volume 2
Labeling images with a computer game
Proceedings of the SIGCHI Conference on Human Factors in Computing Systems
Learning the Kernel Matrix with Semidefinite Programming
The Journal of Machine Learning Research
Probability Estimates for Multi-class Classification by Pairwise Coupling
The Journal of Machine Learning Research
Cross-Generalization: Learning Novel Classes from a Single Example by Feature Replacement
CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 1 - Volume 01
Modeling Scenes with Local Descriptors and Latent Aspects
ICCV '05 Proceedings of the Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1 - Volume 01
Learning Object Categories from Google"s Image Search
ICCV '05 Proceedings of the Tenth IEEE International Conference on Computer Vision - Volume 2
Object Categorization by Learned Universal Visual Dictionary
ICCV '05 Proceedings of the Tenth IEEE International Conference on Computer Vision - Volume 2
Multiple instance learning for sparse positive bags
Proceedings of the 24th international conference on Machine learning
Active learning and logarithmic opinion pools for hpsg parse selection
Natural Language Engineering
Towards Scalable Dataset Construction: An Active Learning Approach
ECCV '08 Proceedings of the 10th European Conference on Computer Vision: Part I
Assessing the costs of sampling methods in active learning for annotation
HLT-Short '08 Proceedings of the 46th Annual Meeting of the Association for Computational Linguistics on Human Language Technologies: Short Papers
Selective supervision: guiding supervised learning with decision-theoretic active learning
IJCAI'07 Proceedings of the 20th international joint conference on Artifical intelligence
Marginalized multi-instance kernels
IJCAI'07 Proceedings of the 20th international joint conference on Artifical intelligence
ECCV'06 Proceedings of the 9th European conference on Computer Vision - Volume Part I
User-Centric Learning and Evaluation of Interactive Segmentation Systems
International Journal of Computer Vision
Annotation propagation in large image databases via dense image correspondence
ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part III
A unifying theory of active discovery and learning
ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part V
Hi-index | 0.00 |
We present an active learning framework that predicts the tradeoff between the effort and information gain associated with a candidate image annotation, thereby ranking unlabeled and partially labeled images according to their expected "net worth" to an object recognition system. We develop a multi-label multiple-instance approach that accommodates realistic images containing multiple objects and allows the category-learner to strategically choose what annotations it receives from a mixture of strong and weak labels. Since the annotation cost can vary depending on an image's complexity, we show how to improve the active selection by directly predicting the time required to segment an unlabeled image. Our approach accounts for the fact that the optimal use of manual effort may call for a combination of labels at multiple levels of granularity, as well as accurate prediction of manual effort. As a result, it is possible to learn more accurate category models with a lower total expenditure of annotation effort. Given a small initial pool of labeled data, the proposed method actively improves the category models with minimal manual intervention.