Authors:
Andreas Christian Müller
and
Sven Behnke
Affiliation:
University of Bonn, Germany
Keyword(s):
Structured Prediction, Image Segmentation, Structured SVMs, Conditional Random Fields.
Related
Ontology
Subjects/Areas/Topics:
Computer Vision, Visualization and Computer Graphics
;
Image and Video Analysis
;
Segmentation and Grouping
Abstract:
Learning structured models using maximum margin techniques has become an indispensable tool for computer
vision researchers, as many computer vision applications can be cast naturally as an image labeling
problem. Pixel-based or superpixel-based conditional random fields are particularly popular examples. Typically,
neighborhood graphs, which contain a large number of cycles, are used. As exact inference in loopy
graphs is NP-hard in general, learning these models without approximations is usually deemed infeasible.
In this work we show that, despite the theoretical hardness, it is possible to learn loopy models exactly in
practical applications. To this end, we analyze the use of multiple approximate inference techniques together
with cutting plane training of structural SVMs. We show that our proposed method yields exact solutions
with an optimality guarantees in a computer vision application, for little additional computational cost. We
also propose a dynamic caching scheme to acc
elerate training further, yielding runtimes that are comparable
with approximate methods. We hope that this insight can lead to a reconsideration of the tractability of loopy
models in computer vision.
(More)