Skip to main content
Article
Bayesian Optimization for Refining Object Proposals
Computer Science Faculty Publications and Presentations
  • Anthony D. Rhodes, Portland State University
  • Jordan Witte, Portland State University
  • Melanie Mitchell, Portland State University
  • Bruno Jedynak, Portland State University
Document Type
Pre-Print
Publication Date
3-1-2017
Subjects
  • Bayesian field theory,
  • Algorithms,
  • Machine learning,
  • Computer vision
Disciplines
Abstract

We develop a general-purpose algorithm using a Bayesian optimization framework for the efficient refinement of object proposals. While recent research has achieved substantial progress for object localization and related objectives in computer vision, current state-of-the-art object localization procedures are nevertheless encumbered by inefficiency and inaccuracy. We present a novel, computationally efficient method for refining inaccurate bounding-box proposals for a target object using Bayesian optimization. Offline, image features from a convolutional neural network are used to train a model to predict an object proposal’s offset distance from a target object. Online, this model is used in a Bayesian active search to improve inaccurate object proposals. In experiments, we compare our approach to a state-of-the-art bounding-box regression method for localization refinement of pedestrian object proposals. Our method exhibits a substantial improvement for the task of localization refinement over this baseline regression method.

Description

Originally published in arXiv.org. This is the author manuscript of a paper submitted for the 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

Persistent Identifier
http://archives.pdx.edu/ds/psu/19538
Citation Information
Rhodes, A. D., Witte, J., Mitchell, M., Jedynak, B., (2017). Bayesian Optimization for Refining Object Proposals arXiv preprint arXiv: arXiv:1703.08653