Active query-driven visual search using probabilistic bisection and convolutional neural networks
share
We present a novel efficient object detection and localization framework based on the probabilistic bisection algorithm. A convolutional neural network 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 provide experimental results on a face localization task that showcase the effectiveness of our approach in comparison to sliding window techniques.
READ FULL TEXT
