S4Net: Single stage salient-instance segmentation

查看全文 作　　者：Ruochen [1]Fan;Ming-Ming [2]Cheng;Qibin [1]Hou;Tai-Jiang [1]Mu;Jingdong [3]Wang;Shi-Min [1]Hu

机构地区：[1]BNRist,Tsinghua University,Beijing,100086,China;[2]Nankai University,Tianjin,300071,China;[3]MSRA,Beijing,100086,China

出　　处：《Computational Visual Media》索引2020年第6卷第2期,共14页

基　　金：supported by National Natural Science Foundation of China(61521002,61572264,61620106008);the National Youth Talent Support Program;Tianjin Natural Science Foundation(17JCJQJC43700,18ZXZNGX00110);the Fundamental Research Funds for the Central Universities(Nankai University,No.63191501)。 摘　　要：In this paper, we consider salient instance segmentation. As well as producing bounding boxes,our network also outputs high-quality instance-level segments as initial selections to indicate the regions of interest. Taking into account the category-independent property of each target, we design a single stage salient instance segmentation framework, with a novel segmentation branch. Our new branch regards not only local context inside each detection window but also the surrounding context, enabling us to distinguish instances in the same scope even with partial occlusion.Our network is end-to-end trainable and is fast(running at 40 fps for images with resolution 320 × 320). We evaluate our approach on a publicly available benchmark and show that it outperforms alternative solutions. We also provide a thorough analysis of our design choices to help readers better understand the function of each part of our network. Source code can be found at http://gffzz188fe103f8f1460as0fpwvovofxxu6uuw.ffgz.tsg.suse.edu.cn/Ruochen Fan/S4 Net. 关键词：salient-instance segmentation salient object detection single stage region-of-interest masking

相关文献

参考文献（70）
引证文献（2）
耦合文献（57）

参考文献(70)

引证文献(2)

耦合文献(57)

互联网出版许可证新出网证(渝)字10号全国400电话 - 免长途话费

S4Net: Single stage salient-instance segmentation

参考文献(70)

引证文献(2)

耦合文献(57)

用户提示