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, [Lecture Notes on Image Processing, Computer Vision, Pattern Recognition, and Graphics, vol. 10496, Springer, 2016], pp. 255–267.
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 multi-layer 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.
@INPROCEEDINGS(http://bigwww.epfl.ch/publications/haubold1701.html,
AUTHOR="Haubold, C. and Uhlmann, V. and Unser, M. and Hamprecht, F.A.",
TITLE="Diverse $M$-Best Solutions by Dynamic Programming",
BOOKTITLE="Proceedings of the Thirty-Ninth German Conference on Pattern
Recognition ({GCPR'17})",
YEAR="2017",
editor="",
volume="10496",
series="Lecture Notes on Image Processing, Computer Vision, Pattern
Recognition, and Graphics",
pages="255--267",
address="Basel BS, Swiss Confederation",
month="September 13-15,",
organization="",
publisher="Springer",
note="")