|M. Pawan Kumar|
LEARNING SPECIFIC-CLASS SEGMENTATION FROM DIVERSE DATA
M. Pawan Kumar, H. Turki, D. Preston and D. Koller
In Proceedings of International Conference on Computer Vision (ICCV), 2011
We consider the task of learning the parameters of a segmentation model that assigns a specific semantic class to each pixel of a given image. The main problem we face is the lack of fully supervised data. We address this issue by developing a principled framework for learning the parameters of a specific-class segmentation model using diverse data. More precisely, we propose a latent structural support vector machine formulation, where the latent variables model any missing information in the human annotation. Of particular interest to us are three types of annotations: (i) images segmented using generic foreground or background classes; (ii) images with bounding boxes specified for objects; and (iii) images labeled to indicate the presence of a class. Using large, publicly available datasets we show that our approach is able to exploit the information present in different annotations to improve the accuracy of a state-of-the art region-based model.
[Paper] [Tech Report - Coming Soon] [Code - Coming Soon]