Improving image categorization by using multiple instance learning with spatial relation

Authors:
Thanh Duc Ngo;Duy-Dinh Le;Shin'ichi Satoh
Affiliations:
The Graduate University for Advanced Studies and National Institute of Informatics, Tokyo, Japan;National Institute of Informatics, Tokyo and The Graduate University for Advanced Studies, Japan;National Institute of Informatics, Tokyo and The Graduate University for Advanced Studies, Japan
Venue:
ICIAP'11 Proceedings of the 16th international conference on Image analysis and processing: Part I
Year:
2011

Citing 8
Cited 0

Solving the multiple instance problem with axis-parallel rectangles

Artificial Intelligence
A framework for multiple-instance learning

NIPS '97 Proceedings of the 1997 conference on Advances in neural information processing systems 10
Image Categorization by Learning and Reasoning with Regions

The Journal of Machine Learning Research
Learning Generative Visual Models from Few Training Examples: An Incremental Bayesian Approach Tested on 101 Object Categories

CVPRW '04 Proceedings of the 2004 Conference on Computer Vision and Pattern Recognition Workshop (CVPRW'04) Volume 12 - Volume 12
A Critical View of Context

International Journal of Computer Vision
MILES: Multiple-Instance Learning via Embedded Instance Selection

IEEE Transactions on Pattern Analysis and Machine Intelligence
Context based object categorization: A critical survey

Computer Vision and Image Understanding
Context modeling in computer vision: techniques, implications, and applications

Multimedia Tools and Applications

Quantified Score

Hi-index	0.00

Visualization

Abstract

Image categorization is a challenging problem when a label is provided for the entire training image only instead of the object region. To eliminate labeling ambiguity, image categorization and object localization should be performed simultaneously. Discriminative Multiple Instance Learning (MIL) can be used for this task by regarding each image as a bag and sub-windows in the image as instances. Learning a discriminative MI classifier requires an iterative solution. In each round, positive sub-windows for the next round should be selected. With standard approaches, selecting only one positive sub-window per positive bag may limit the search space for global optimum; meanwhile, selecting all temporal positive sub-windows may add noise into learning. We select a subset of sub-windows per positive bag to avoid those limitations. Spatial relations between sub-windows are used as clues for selection. Experimental results demonstrate that our approach outperforms previous discriminative MIL approaches and standard categorization approaches.