2013 · 61 citations · 24 references
ComputingComputer ScienceComputer VisionMachine LearningMachine VisionDeep LearningImage SegmentationInstance SegmentationPattern RecognitionScene UnderstandingSemantic SegmentationDiverse Re-rankingExplorationModel RankingRe-rankingSegmentationSolution Space DesignSolution Space Exploration
This paper introduces a hybrid, two-stage approach to semantic image segmentation. In the first stage a probabilistic model generates a set of diverse plausible segmentations. In the second stage, a discriminatively trained re-ranking model selects the best segmentation from this set. The re-ranking stage can use much more complex features than what could be tractably used in the probabilistic model, allowing a better exploration of the solution space than possible by simply producing the most probable solution from the probabilistic model. While our proposed approach already achieves state-of-the-art results (48%) on the challenging VOC 2012 dataset, our machine and human analyses suggest that even larger gains are possible with such an approach.
24
The Pascal Visual Object Classes (VOC) Challenge
Mark Everingham, Luc Van Gool, Christopher K. I. Williams et al. · International Journal of Computer Vision · 2009 · 19.5K citations · Full text
Robust Real-Time Face Detection
Paul Viola, Michael Jones · International Journal of Computer Vision · 2004 · 14.2K citations
Cutting-plane training of structural SVMs
Thorsten Joachims, Thomas Finley, Chun-Nam Yu · Machine Learning · 2009 · 980 citations · Full text