OPT OpenIR  > 光学影像学习与分析中心
GAN and DCN based multi-step supervised learning for image semantic segmentation
Fang, Jie1,2; Cao, Xiaoqian3
2018
会议名称1st Chinese Conference on Pattern Recognition and Computer Vision, PRCV 2018
会议录名称Pattern Recognition and Computer Vision - First Chinese Conference, PRCV 2018, Proceedings
卷号11257 LNCS
页码28-40
会议日期2018-11-23
会议地点Guangzhou, China
出版者Springer Verlag
产权排序1
摘要

Image semantic segmentation contains two sub-tasks, segmenting and labeling. However, the recent fully convolutional network (FCN) based methods often ignore the first sub-task and consider it as a direct labeling one. Even though these methods have achieved competitive performances, they obtained spatially fragmented and disconnected outputs. The reason is that, pixel-level relationships inside the deepest layers become inconsistent since traditional FCNs do not have any explicit pixel grouping mechanism. To address this problem, a multi-step supervised learning method, which contains image-level supervised learning step and pixel-level supervised learning step, is proposed. Specifically, as for the visualized result of image semantic segmentation, it is actually an image-to-image transformation problem, from RGB domain to category label domain. The recent conditional generative adversarial network (cGAN) has achieved significant performance for image-to-image generation task, and the generated image remains good regional connectivity. Therefore, a cGAN supervised by RGB-category label map is used to obtain a coarse segmentation mask, which avoids generating disconnected segmentation results to a certain extent. Furthermore, an interaction information (II) loss term is proposed for cGAN to remain the spatial structure of the segmentation mask. Additionally, dilated convolutional networks (DCNs) have achieved significant performance in object detection field, especially for small objects because of its special receptive field settings. Specific to image semantic segmentation, if each pixel is seen as an object, this task can be transformed to object detection. In this case, combined with the segmentation mask from cGAN, a DCN supervised by the pixel-level label is used to finalize the category recognition of each pixel in the image. The proposed method achieves satisfactory performances on three public and challenging datasets for image semantic segmentation. ? Springer Nature Switzerland AG 2018.

作者部门光学影像学习与分析中心
DOI10.1007/978-3-030-03335-4_3
收录类别EI
ISBN号9783030033347
语种英语
ISSN号03029743;16113349
EI入藏号20184806152603
引用统计
文献类型会议论文
条目标识符http://ir.opt.ac.cn/handle/181661/30869
专题光学影像学习与分析中心
通讯作者Fang, Jie
作者单位1.Center for OPTical IMagery Analysis and Learning (OPTIMAL), Xi’an Institute of Optics and Precision Mechanics, Chinese Academy of Sciences, Xi’an; Shaanxi; 710119, China;
2.University of Chinese Academy of Sciences, 19A Yuquanlu, Beijing; 100049, China;
3.College of Electrical and Information Engineering, Shaanxi University of Science and Technology, Xi’an; Shaanxi; 710021, China
推荐引用方式
GB/T 7714
Fang, Jie,Cao, Xiaoqian. GAN and DCN based multi-step supervised learning for image semantic segmentation[C]:Springer Verlag,2018:28-40.
条目包含的文件
文件名称/大小 文献类型 版本类型 开放类型 使用许可
GAN and DCN based mu(997KB)会议论文 开放获取CC BY-NC-SA请求全文
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
[Fang, Jie]的文章
[Cao, Xiaoqian]的文章
百度学术
百度学术中相似的文章
[Fang, Jie]的文章
[Cao, Xiaoqian]的文章
必应学术
必应学术中相似的文章
[Fang, Jie]的文章
[Cao, Xiaoqian]的文章
相关权益政策
暂无数据
收藏/分享
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。