Auto-context and its Application to High-level Vision Tasks

Auto-context and its Application to High-level Vision Tasks

Cached

Download Links

[www.loni.ucla.edu]

Other Repositories/Bibliography

DBLP

by Zhuowen Tu , Xiang Bai

Venue:	In Proc. CVPR
Citations:	40 - 1 self

Versions

Version History

Metadata Version 1

Datum	Value	Source
TITLE	Auto-context and its Application to High-level Vision Tasks	INFERENCE
AUTHOR NAME	Zhuowen Tu	SVM HeaderParse 0.2
AUTHOR AFFIL	Lab of Neuro Imaging, University of California, Los Angeles	SVM HeaderParse 0.2
AUTHOR NAME	Xiang Bai	SVM HeaderParse 0.2
AUTHOR AFFIL	Lab of Neuro Imaging, University of California, Los Angeles	SVM HeaderParse 0.2
ABSTRACT	The notion of using context information for solving high-level vision and medical image segmentation problems has been increasingly realized in the field. However, how to learn an effective and efficient context model, together with an image appearance model, remains mostly unknown. The current literature using Markov Random Fields (MRFs) and Conditional Random Fields (CRFs) often involves specific algorithm design, in which the modeling and computing stages are studied in isolation. In this paper, we propose the auto-context algorithm. Given a set of training images and their corresponding label maps, we first learn a classifier on local image patches. The discriminative probability (or classification confidence) maps created by the learned classifier are then used as context information, in addition to the original image patches, to train a new classifier. The algorithm then iterates until convergence. Auto-context integrates low-level and context information by fusing a large number of low-level appearance features with context and implicit shape information. The resulting discriminative algorithm is general and easy to implement. Under nearly the same parameter settings in training, we apply the algorithm to three challenging vision applications: foreground/background segregation, human body configuration estimation, and scene region labeling. Moreover, context also plays a very important role in medical/brain images where the anatomical structures are mostly constrained to relatively fixed positions. With only some slight changes resulting from using 3D instead of 2D features, the auto-context algorithm applied to brain MRI image segmentation is shown to outperform state-of-the-art algorithms specifically designed for this domain. Furthermore, the scope of the proposed algorithm goes beyond image analysis and it has the potential to be used for a wide variety of problems in multi-variate labeling.	SVM HeaderParse 0.2
VENUE	In Proc. CVPR	INFERENCE
VENUE TYPE	CONFERENCE	INFERENCE
CITATIONS	55 found	ParsCit 1.0