English

Active query-driven visual search using probabilistic bisection and convolutional neural networks

Computer Vision and Pattern Recognition 2020-02-28 v3

Abstract

We present a novel efficient object detection and localization framework based on the probabilistic bisection algorithm. A Convolutional Neural Network (CNN) is trained and used as a noisy oracle that provides answers to input query images. The responses along with error probability estimates obtained from the CNN are used to update beliefs on the object location along each dimension. We show that querying along each dimension achieves the same lower bound on localization error as the joint query design. Finally, we compare our approach to the traditional sliding window technique on a real world face localization task and show speed improvements by at least an order of magnitude while maintaining accurate localization.

Keywords

Cite

@article{arxiv.1806.11223,
  title  = {Active query-driven visual search using probabilistic bisection and convolutional neural networks},
  author = {Athanasios Tsiligkaridis and Theodoros Tsiligkaridis},
  journal= {arXiv preprint arXiv:1806.11223},
  year   = {2020}
}

Comments

5 pages, 4 figures, 1 table

R2 v1 2026-06-23T02:45:32.893Z