Bayesian field theory, Algorithms, Machine learning, Computer vision
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.
Rhodes, A. D., Witte, J., Mitchell, M., Jedynak, B., (2017). Bayesian Optimization for Refining Object Proposals arXiv preprint arXiv: arXiv:1703.08653