Knowledge Commons of Institute of Automation,CAS
Weakly Supervised RBM for Semantic Segmentation | |
Yong Li; Jing Liu; Yuhang Wang; Hanqing Lu; Songde Ma | |
2015 | |
会议名称 | International Joint Conference on Artificial Intelligence |
会议录名称 | Proceedings of the Twenty-Fourth International Joint Conference on Artificial Intelligence |
会议日期 | July 25-31, 2015 |
会议地点 | Buenos Aires, Argentina |
摘要 | In this paper, we propose a weakly supervised Restricted Boltzmann Machines (WRBM) approach to deal with the task of semantic segmentation with only image-level labels available. In WRBM, its hidden nodes are divided into multiple blocks, and each block corresponds to a specific label. Accordingly, semantic segmentation can be directly modeled by learning the mapping from visible layer to the hidden layer of WRBM. Specifically, based on the standard RBM, we import another two terms to make full use of image-level labels and alleviate the effect of noisy labels. First, we expect the hidden response of each superpixel is suppressed on the labels outside its parent image-level label set, and a non-image-level label suppression term is formulated to implicitly import the image-level labels as weak supervision. Second, semantic graph propagation is employed to exploit the cooccurrence between visually similar regions and labels. Besides, we deal with the problems of label imbalance and diverse backgrounds by adapting the block size to the label frequency and appending hidden response blocks corresponding to backgrounds respectively. Extensive experiments on two real-world datasets demonstrate the good performance of our approach compared with some state-of-the-art methods. |
关键词 | 无 |
收录类别 | EI |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/11766 |
专题 | 紫东太初大模型研究中心_图像与视频分析 |
通讯作者 | Jing Liu |
推荐引用方式 GB/T 7714 | Yong Li,Jing Liu,Yuhang Wang,et al. Weakly Supervised RBM for Semantic Segmentation[C],2015. |
条目包含的文件 | 下载所有文件 | |||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
IJCAI15-268.pdf(1527KB) | 会议论文 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论