Learning From Noisy Labels Via Meta Credible Label Elicitation

Weakly Supervised Object Detection (WSOD) aims to train a detector to specify the interesting targets in an image by only using image-level labels. An important trend of current WSOD methods is to integrate object detection with Weakly Supervised Semantic Segmentation (WSSS), so that more discriminative regions can be obtained and more accurate detection can be achieved. However, due to the unreliable segmentation supervision generated by WSOD, their performance is still very limited. To address this problem, in this paper, we propose a novel end-to-end framework termed Class activation map Guided Detection Network (CGDN), where the detection process is guided by Class Activation Map (CAM) rather than the segmentation results. The proposed CGDN is composed of a detection branch and a CAM refinement branch, where the CAM refinement branch critically refines the CAMs generated by the detection branch, and then the refined CAMs are deployed to provide more reliable foreground cues for the detection branch in turn. Therefore, the two branches interact which leads to progressively improved detection and CAM outputs. Extensive experiments on PASCAL VOC 2007 and 2012 datasets verify the effectiveness of our proposed network.