CASIA OpenIR  > 精密感知与控制研究中心  > 精密感知与控制
Learning Dynamic Routing for Semantic Segmentation
Li, Yanwei1,2; Song, Lin3; Chen, Yukang1,2; Li, Zeming4; Zhang, Xiangyu4; Wang, Xingang1; Sun, Jian4
2020
Conference NameIEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Conference Date2020.6.14-2020.6.19
Conference Place美国西雅图(改为线上)
PublisherIEEE
Abstract

Recently, numerous handcrafted and searched networks have been applied for semantic segmentation. However, previous works intend to handle inputs with various scales in pre-defined static architectures, such as FCN, U-Net, and DeepLab series. This paper studies a conceptually new method to alleviate the scale variance in semantic representation, named dynamic routing. The proposed framework generates data-dependent routes, adapting to the scale distribution of each image. To this end, a differentiable gating function, called soft conditional gate, is proposed to select scale transform paths on the fly. In addition, the computational cost can be further reduced in an end-to-end manner by giving budget constraints to the gating function. We further relax the network level routing space to support multi-path propagations and skip-connections in each forward, bringing substantial network capacity. To demonstrate the superiority of the dynamic property, we compare with several static architectures, which can be modeled as special cases in the routing space. Extensive experiments are conducted on Cityscapes and PASCAL VOC 2012 to illustrate the effectiveness of the dynamic framework. Code is available at https://github.com/yanwei-li/DynamicRouting.

Indexed ByEI
Language英语
Document Type会议论文
Identifierhttp://ir.ia.ac.cn/handle/173211/39163
Collection精密感知与控制研究中心_精密感知与控制
Corresponding AuthorWang, Xingang
Affiliation1.Institute of Automation, Chinese Academy of Sciences
2.University of Chinese Academy of Sciences
3.Xi’an Jiaotong University
4.Megvii Technology
First Author AffilicationInstitute of Automation, Chinese Academy of Sciences
Corresponding Author AffilicationInstitute of Automation, Chinese Academy of Sciences
Recommended Citation
GB/T 7714
Li, Yanwei,Song, Lin,Chen, Yukang,et al. Learning Dynamic Routing for Semantic Segmentation[C]:IEEE,2020.
Files in This Item: Download All
File Name/Size DocType Version Access License
main.pdf(3982KB)会议论文 开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Li, Yanwei]'s Articles
[Song, Lin]'s Articles
[Chen, Yukang]'s Articles
Baidu academic
Similar articles in Baidu academic
[Li, Yanwei]'s Articles
[Song, Lin]'s Articles
[Chen, Yukang]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Li, Yanwei]'s Articles
[Song, Lin]'s Articles
[Chen, Yukang]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: main.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.