Active query-driven visual search using probabilistic bisection and convolutional neural networks
This provides faster object localization for computer vision applications, though it appears incremental as it adapts existing probabilistic bisection to CNNs.
The paper tackles object detection and localization by combining probabilistic bisection with a CNN as a noisy oracle, achieving at least 10x speed improvement over sliding window methods while maintaining accurate face localization.
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.