Semi- and Weakly- Supervised Semantic Segmentation with Deep Convolutional Neural Networks
Yuhang Wang; Jing Liu; Yong Li; Hanqing Lu
2015
会议名称ACM Conference on Multimedia Conference
会议录名称Proceedings of the 23rd Annual ACM Conference on Multimedia Conference
会议日期October 26 - 30, 2015
会议地点Brisbane, Australia
摘要Successful semantic segmentation methods typically rely on the training datasets containing a large number of pixel-wise labeled images. To alleviate the dependence on such a fully annotated training dataset, in this paper, we propose a semi- and weakly-supervised learning framework by exploring images most only with image-level labels and very few with pixel-level labels, in which two stages of Convolutional Neural Network (CNN) training are included. First, a pixel-level supervised CNN is trained on very few fully annotated images. Second, given a large number of images with only image-level labels available, a collaborative-supervised CNN is designed to jointly perform the pixel-level and image-level classification tasks, while the pixel-level labels are predicted by the fully-supervised network in the first stage. The collaborative-supervised network can remain the discriminative ability of the fully-supervised model learned with fully labeled images, and further enhance the performance by importing more weakly labeled data. Our experiments on two challenging datasets, i.e, PASCAL VOC 2007 and LabelMe LMO, demonstrate the satisfactory performance of our approach, nearly matching the results achieved when all training images have pixel-level labels.
关键词Cnn Semantic Segmentation Semi-supervised Learning
文献类型会议论文
条目标识符http://ir.ia.ac.cn/handle/173211/13444
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
作者单位中国科学院自动化研究所
推荐引用方式
GB/T 7714
Yuhang Wang,Jing Liu,Yong Li,et al. Semi- and Weakly- Supervised Semantic Segmentation with Deep Convolutional Neural Networks[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
Semi- and Weakly- Su(1284KB)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
[Yuhang Wang]的文章
[Jing Liu]的文章
[Yong Li]的文章
百度学术
百度学术中相似的文章
[Yuhang Wang]的文章
[Jing Liu]的文章
[Yong Li]的文章
必应学术
必应学术中相似的文章
[Yuhang Wang]的文章
[Jing Liu]的文章
[Yong Li]的文章
相关权益政策
暂无数据
收藏/分享
文件名: Semi- and Weakly- Supervised Semantic Segmentation with Deep Convolutional Neural Networks.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。