Object proposal generation applying the distance dependent Chinese restaurant process
This work addresses the need for uncertainty representation in robotics environments, offering a method that goes beyond single best guesses.
The paper tackles the problem of generating object proposals with uncertainty quantification for robotics applications, achieving state-of-the-art performance on an indoor object discovery dataset while providing a likelihood term for ranking proposals.
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.