Fast Postprocessing for Difficult Discrete Energy Minimization Problems
| Autor: | Richard Hartley, Loong Fah Cheong, Ijaz Akhter |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
business.industry
Computer science Binary number 02 engineering and technology 010501 environmental sciences Directed acyclic graph Energy minimization 01 natural sciences Shortest path problem Core (graph theory) 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing Artificial intelligence business Algorithm Approximate solution 0105 earth and related environmental sciences |
| Zdroj: | WACV |
| DOI: | 10.1109/wacv45572.2020.9093369 |
| Popis: | Despite the rapid progress in discrete energy minimization, certain problems involving high connectivity and a high number of labels are considered very hard but are still very relevant in computer vision. We propose a post-processing technique to improve the sub-optimal results of the existing methods on such problems. Our core contribution is a mapping between the binary min-cut problem and finding the shortest path in a directed acyclic graph. Using this mapping, we present an algorithm to find an approximate solution for the min-cut problem. We also extend the same idea for multi-label factor-graphs in the form of an iterative move-making algorithm. The proposed algorithm is extremely fast, yet outperforms the existing techniques in terms of accuracy as well as the computational time. We demonstrate competitive or better results on problems where already high-quality work is done. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|