Weakly Supervised Object Boundaries

Khoreva, Anna and Benenson, Rodrigo and Omran, Mohamed and Hein, Matthias and Schiele, Bernt
(2016) Weakly Supervised Object Boundaries.
In: 29th IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2016).
Conference: CVPR IEEE Conference on Computer Vision and Pattern Recognition

Full text not available from this repository.


State-of-the-art learning based boundary detection methods require extensive training data. Since labelling object boundaries is one of the most expensive types of annotations, there is a need to relax the requirement to carefully annotate images to make both the training more affordable and to extend the amount of training data. In this paper we propose a technique to generate weakly supervised annotations and show that bounding box annotations alone suffice to reach high-quality object boundaries without using any object-specific boundary annotations. With the proposed weak supervision techniques we achieve the top performance on the object boundary detection task, outperforming by a large margin the current fully supervised state-of-the-art methods.


Actions (login required)

View Item View Item