DMCA
Multiple-Instance Learning for Natural Scene Classification (1998)
| Venue: | In The Fifteenth International Conference on Machine Learning |
| Citations: | 229 - 2 self |
BibTeX
@INPROCEEDINGS{Maron98multiple-instancelearning,
author = {Oded Maron and Aparna Lakshmi Ratan},
title = {Multiple-Instance Learning for Natural Scene Classification},
booktitle = {In The Fifteenth International Conference on Machine Learning},
year = {1998},
pages = {341--349},
publisher = {Morgan Kaufmann}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
Multiple-Instance learning is a way of modeling ambiguity in supervised learning examples. Each example is a bag of instances, but only the bag is labeled - not the individual instances. A bag is labeled negative if all the instances are negative, and positive if at least one of the instances in positive. We apply the Multiple-Instance learning framework to the problem of learning how to classify natural images. Images are inherently ambiguous since they can represent many different things. A user labels an image as positive if the image somehow contains the concept. Each image is a bag, and the instances are various sub-regions in the image. From a small collection of positive and negative examples, we can learn the concept and then use it to retrieve images that contain the concept from a large database. We show that the Diverse Density algorithm performs well in this task, that simple hypothesis classes are sufficient to classify natural images, and that user interaction helps to im...
Keyphrases
multiple-instance learning natural scene classification natural image small collection diverse density algorithm performs image somehow supervised learning example various sub-regions negative example many different thing individual instance multiple-instance learning framework simple hypothesis class user interaction large database
