Large Scale Hard Sample Mining with Monte Carlo Tree Search

We investigate an efficient strategy to collect false positives from very large training sets in the context of object detection. Our approach scales up the standard bootstrapping procedure by using a hierarchical decomposition of an image collection which reflects the statistical regularity of the detector's responses. Based on that decomposition, our procedure uses a Monte Carlo Tree Search to prioritize the sampling toward sub-families of images which have been observed to be rich in false positives, while maintaining a fraction of the sampling toward unexplored sub-families of images. The resulting procedure increases substantially the proportion of false positive samples among the visited ones compared to a naive uniform sampling. We apply experimentally this new procedure to face detection with a collection of similar to 100,000 background images and to pedestrian detection with similar to 32,000 images. We show that for two standard detectors, the proposed strategy cuts the number of images to visit by half to obtain the same amount of false positives and the same final performance.