Multiple-instance learning with structured bag models

Authors:
Jonathan Warrell;Philip H. S. Torr
Affiliations:
Oxford Brookes University, Oxford, UK;Oxford Brookes University, Oxford, UK
Venue:
EMMCVPR'11 Proceedings of the 8th international conference on Energy minimization methods in computer vision and pattern recognition
Year:
2011

Citing 7
Cited 0

Cosegmentation of Image Pairs by Histogram Matching - Incorporating a Global Constraint into MRFs

CVPR '06 Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 1
Robust Higher Order Potentials for Enforcing Label Consistency

International Journal of Computer Vision
Multi-instance learning by treating instances as non-I.I.D. samples

ICML '09 Proceedings of the 26th Annual International Conference on Machine Learning
Cosegmentation revisited: models and optimization

ECCV'10 Proceedings of the 11th European conference on Computer vision: Part II
Graph cut based inference with co-occurrence statistics

ECCV'10 Proceedings of the 11th European conference on Computer vision: Part V
MIForests: multiple-instance learning with randomized trees

ECCV'10 Proceedings of the 11th European conference on Computer vision: Part VI
TextonBoost: joint appearance, shape and context modeling for multi-class object recognition and segmentation

ECCV'06 Proceedings of the 9th European conference on Computer Vision - Volume Part I

Quantified Score

Hi-index	0.00

Visualization

Abstract

Traditional approaches to Multiple-Instance Learning (MIL) operate under the assumption that the instances of a bag are generated independently, and therefore typically learn an instance-level classifier which does not take into account possible dependencies between instances. This assumption is particularly inappropriate in visual data, where spatial dependencies are the norm. We introduce here techniques for incorporating MIL constraints into Conditional Random Field models, thus providing a set of tools for constructing structured bag models, in which spatial (or other) dependencies are represented. Further, we show how Deterministic Annealing, which has proved a successful method for training non-structured MIL models, can also form the basis of training models with structured bags. Results are given on various segmentation tasks.