Paper Info
Title
Multiple-instance learning with structured bag models
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.
Year
DOI
Venue
2011
10.1007/978-3-642-23094-3_27
EMMCVPR
Keywords
Field
DocType
structured bag model,structured bag,spatial dependency,mil model,mil constraint,training model,deterministic annealing,multiple-instance learning,account possible dependency,conditional random field model
Conditional random field,Computer science,Segmentation,Deterministic annealing,Artificial intelligence,Classifier (linguistics),Machine learning
Conference
Citations 
PageRank 
References 
5
0.42
22
Authors
2
Name
Order
Citations
PageRank
Jonathan Warrell149418.95
Philip H. S. Torr29140636.18