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
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
专题模式识别国家重点实验室_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
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Yong Li]的文章
[Jing Liu]的文章
[Yuhang Wang]的文章
百度学术
百度学术中相似的文章
[Yong Li]的文章
[Jing Liu]的文章
[Yuhang Wang]的文章
必应学术
必应学术中相似的文章
[Yong Li]的文章
[Jing Liu]的文章
[Yuhang Wang]的文章
相关权益政策
暂无数据
收藏/分享
文件名: IJCAI15-268.pdf
格式: Adobe PDF
所有评论 (0)
暂无评论
 

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。