Diverse M-Best Solutions by Dynamic Programming
C. Haubold, V. Uhlmann, M. Unser, F.A. Hamprecht
Proceedings of the Thirty-Ninth German Conference on Pattern Recognition (GCPR'17), Basel BS, Swiss Confederation, September 13-15, 2017, in press.
Please do not bookmark the In Press papers as content and presentation may differ from the published version.
In a few seconds, you should be redirected to the published version. The preprint version is still available here
Many computer vision pipelines involve dynamic programming primitives such as finding a shortest path or the minimum energy solution in a tree-shaped probabilistic graphical model. In such cases, extracting not merely the best, but the set of M-best solutions is useful to generate a rich collection of candidate proposals that can be used in downstream processing. In this work, we show how M-best solutions of tree-shaped graphical models can be obtained by dynamic programming on a special graph with M layers. The proposed multilayer concept is optimal for searching M-best solutions, and so flexible that it can also approximate M-best diverse solutions. We illustrate the usefulness with applications to object detection, panorama stitching and centerline extraction.
Supplementary material
- Supplementary Note (PDF file) (2.8 MB). 1) Optimal Second Best Tree Solutions: Graph Construction 2) Approximate Diverse M-Best Solutions 3) Applications and Experiments.