Object Proposal Generation Applying the Distance Dependent Chinese Restaurant Process
Published in
Scandinavian Conference on Image Analysis(2017)External Links:
TL
TL;DR
This paper proposes object proposal generation based on non-parametric Bayesian inference that allows quantification of the likelihood of the proposals, and applies Markov chain Monte Carlo to draw samples of image segmentations via the distance dependent Chinese restaurant process.
Abstract
In application domains such as robotics, it is useful to represent the uncertainty related to the robot’s belief about the state of its environment. Algorithms that only yield a single “best guess” as a result are not sufficient. In this paper, we propose object proposal generation based on non-parametric Bayesian inference that allows quantification of the likelihood of the proposals. We apply Markov chain Monte Carlo to draw samples of image segmentations via the distance dependent Chinese restaurant process. Our method achieves state-of-the-art performance on an indoor object discovery data set, while additionally providing a likelihood term for each proposal. We show that the likelihood term can effectively be used to rank proposals according to their quality.
References16 items
1
Latent Marked Poisson Process with Applications to Object Segmentation
2
Saliency-Guided Object Candidates Based on Gestalt Principles
3
Sequence-level object candidates based on saliency for generic object recognition on mobile systems
4
Decision making under uncertain segmentations
5