Rethinking Segmentation Guidance for Weakly Supervised Object Detection

Weakly supervised object detection aims at learning object detectors with only image-level category labels. Most existing methods tend to solve this problem by using a multiple instance learning detector which is usually trapped to discriminate object parts, rather than the entire object. In order to select high-quality proposals, recent works leverage objectness scores derived from weakly-supervised segmentation maps to rank the object proposals. Base our observation, this kind of segmentation guided method always fails due to neglect of the fact that objectness of all proposals inside the ground-truth box should be consistent. In this paper, we propose a novel object representation named Objectness Consistent Representation (OCR) to meet the consistency criterion of objectness. Specifically, we project the segmentation confidence scores into two orthogonal directions, namely vertical and horizontal, to get the OCR. With the novel object representation, more high-quality proposals can be mined for learning a much stronger object detector. We obtain 54.6% and 51.1% mAP scores on VOC 2007 and 2012 datasets, significantly outperforming the state-of-the-arts and demonstrating the superiority of OCR for weakly supervised object detection.