4.6 Article

Deep graph cut network for weakly-supervised semantic segmentation

期刊

SCIENCE CHINA-INFORMATION SCIENCES
卷 64, 期 3, 页码 -

出版社

SCIENCE PRESS
DOI: 10.1007/s11432-020-3065-4

关键词

semantic segmentation; weakly-supervised learning; semi-supervised learning; graph cut

资金

  1. National Natural Science Foundation of China [61876212, 61733007]
  2. Zhejiang Lab [2019NB0AB02]

向作者/读者索取更多资源

This paper proposes a weakly-supervised task for pixel-level semantic segmentation using semi-supervised learning methods, achieving fine segmentation from image-level labels. Combining the graph cut algorithm with activation seeds generated by a classification network provides effective supervision information, leading to successful experimental results.
The scarcity of fully-annotated data becomes the biggest obstacle that prevents many deep learning approaches from widely applied. Weakly-supervised visual learning which can utilize inexact annotations is developed rapidly to remedy such a situation. In this paper, we study the weakly-supervised task achieving pixel-level semantic segmentation only with image-level labels as supervision. Different from other methods, our approach tries to transform the weakly-supervised visual learning problem into a semi-supervised visual learning problem and then utilizes semi-supervised learning methods to solve it. Utilizing this transformation, we can adopt effective semi-supervised methods to perform transductive learning with context information. In the semi-supervised learning module, we propose to use the graph cut algorithm to label more supervision from the activation seeds generated from a classification network. The generated labels can provide the segmentation model with effective supervision information; moreover, the graph cut module can benefit from features extracted by the segmentation model. Then, each of them updates and optimizes the other iteratively until convergence. Experiment results on PASCAL VOC and COCO benchmarks demonstrate the effectiveness of the proposed deep graph cut algorithm for weakly-supervised semantic segmentation.

作者

我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。

评论

主要评分

4.6
评分不足

次要评分

新颖性
-
重要性
-
科学严谨性
-
评价这篇论文

推荐

暂无数据
暂无数据