Learning To Segment Under Various Forms Of Weak Supervision
2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)(2015)
摘要
Despite the promising performance of conventional fully supervised algorithms, semantic segmentation has remained an important, yet challenging task. Due to the limited availability of complete annotations, it is of great interest to design solutions for semantic segmentation that take into account weakly labeled data, which is readily available at a much larger scale. Contrasting the common theme to develop a different algorithm for each type of weak annotation, in this work, we propose a unified approach that incorporates various forms of weak supervision - image level tags, bounding boxes, and partial labels - to produce a pixel-wise labeling. We conduct a rigorous evaluation on the challenging Siftflow dataset for various weakly labeled settings, and show that our approach outperforms the stateof-the-art by 12% on per-class accuracy, while maintaining comparable per-pixel accuracy.
更多查看译文
关键词
semantic segmentation,weakly labeled data,weak annotation,weak supervision,image level tags,bounding boxes,partial labels,pixel-wise labeling,Siftflow dataset
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