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 with
the state-of-the-arts.
Type de document :
Communication dans un congrès
International Conference on Image Processing (ICIP), Oct 2014, Paris, France. pp.4072-4076, 2014
https://hal.archives-ouvertes.fr/hal-01301105
Contributeur : Équipe Gestionnaire Des Publications Si Liris <>
Soumis le : lundi 11 avril 2016 - 16:30:12
Dernière modification le : lundi 25 avril 2016 - 13:48:31
Yuxing Tang, Xiaofang Wang, Emmanuel Dellandréa, Simon Masnou, Liming Chen. Fusing Generic Objectness and Deformable Part-based Models for Weakly Supervised Object Detection. International Conference on Image Processing (ICIP), Oct 2014, Paris, France. pp.4072-4076, 2014. <hal-01301105>
