Fusing Generic Objectness and Deformable Part-based Models for Weakly Supervised Object Detection

Abstract : In the context of lack of object-level annotation, we propose a model that enhances the weakly supervised deformable part model (DPM) by emphasizing the importance of size and aspect ratio of the initial class-specific root filter. For each image, to extract a reliable bounding box as this root filter estimate, we explore the generic objectness measurement to obtain a reference window based on the most salient region, and select a small set of candidate windows by adaptive thresholding and greedy Non-Maximum Suppression (NMS). The initial root filter estimate is decided by optimizing the score of overlap between the reference box and candidate boxes, as well as their corresponding objectness score. Then the derived window is treated as a positive training window for DPM training. Finally, we design a flexible enlarging-and shrinking post-processing procedure to modify the output of DPM, which can effectively fit to the aspect ratio of the object and further improve the final accuracy. Experimental results on the challenging PASCAL VOC 2007 database demonstrate that our proposed framework is effective and competitive withthe state-of-the-arts.