Weakly-Supervised Salient Object Detection With Saliency Bounding Boxes
IEEE TRANSACTIONS ON IMAGE PROCESSING(2021)
摘要
In this paper, we propose a novel form of weak supervision for salient object detection (SOD) based on saliency bounding boxes, which are minimum rectangular boxes enclosing the salient objects. Based on this idea, we propose a novel weakly-supervised SOD method, by predicting pixel-level pseudo ground truth saliency maps from just saliency bounding boxes. Our method first takes advantage of the unsupervised SOD methods to generate initial saliency maps and addresses the over/under prediction problems, to obtain the initial pseudo ground truth saliency maps. We then iteratively refine the initial pseudo ground truth by learning a multi-task map refinement network with saliency bounding boxes. Finally, the final pseudo saliency maps are used to supervise the training of a salient object detector. Experimental results show that our method outperforms state-of-the-art weakly-supervised methods.
更多查看译文
关键词
Object detection, Annotations, Detectors, Training, Proposals, Computer science, Task analysis, Saliency bounding boxes, salient object detection, weak supervision
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要