Diverse M-Best Solutions by Dynamic Programming
| Autor: | Haubold, Carsten, Uhlmann, Virginie, Unser, Michael, Hamprecht, Fred A. |
|---|---|
| Rok vydání: | 2018 |
| Předmět: | |
| Zdroj: | Haubold, C., Uhlmann, V., Unser, M., Hamprecht, F. A.: Diverse M-best solutions by dynamic programming. In: Roth, V., Vetter, T. (eds.) Pattern Recognition. GCPR 2017. vol 10496, pp. 255-267. Springer, Cham (2017) |
| Druh dokumentu: | Working Paper |
| DOI: | 10.1007/978-3-319-66709-6_21 |
| Popis: | 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. Note: We have observed that an assumption in section 4 of our paper is not always fulfilled, see the attached corrigendum for details. Comment: Includes supplementary and corrigendum |
| Databáze: | arXiv |
| Externí odkaz: |
|