Knowledge Commons of Institute of Automation,CAS
Semantic Segmentation with Modified Deep Residual Networks | |
Chen, Xinze1,2; Chen, Guangliang1,2; Cai, Yinghao1; Wen, Dayong1; Li, Heping1 | |
2016-10 | |
会议名称 | Chinese Conference on Pattern Recognition(CCPR) |
会议录名称 | Proceedings of Chinese Conference on Pattern Recognition |
会议日期 | November, 2016 |
会议地点 | Cheng Du, China |
摘要 | A novel semantic segmentation method is proposed, which consists of the following three parts: (I) First, a simple yet effective data augmentation method is introduced without any extra GPU memory cost during training. (II) Second, a deeper residual network is constructed through three effective techniques: dilated convolution, LSTM network and multi-scale prediction. (III) Third, an online hard pixels mining is adopted to improve the segmentation performance. We combine these three parts to train an end-to-end network and achieve a new state-ofthe-art segmentation accuracy of 79.3% on PASCAL VOC 2012 test set at the time of submission. |
关键词 | Semantic Segmentation Data Augmentation Residual Networks Lstm Multi-scale Prediction |
收录类别 | EI |
语种 | 英语 |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/14458 |
专题 | 多模态人工智能系统全国重点实验室_机器人视觉 |
通讯作者 | Li, Heping |
作者单位 | 1.中国科学院自动化研究所 2.中国科学院大学 |
第一作者单位 | 中国科学院自动化研究所 |
通讯作者单位 | 中国科学院自动化研究所 |
推荐引用方式 GB/T 7714 | Chen, Xinze,Chen, Guangliang,Cai, Yinghao,et al. Semantic Segmentation with Modified Deep Residual Networks[C],2016. |
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 | ||
Semantic Segmentatio(2516KB) | 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