CASIA OpenIR  > 智能感知与计算研究中心
Box-driven Class-wise Region Masking and Filling Rate Guided Loss for Weakly Supervised Semantic Segmentation
Song, Chunfeng1,2; Huang, Yang1,2; Ouyang, Wanli3; Wang, Liang1,2,4,5
2019-06
Conference NameIEEE International Conference on Computer Vision and Pattern Recognition (CVPR)
Conference Date2019-6
Conference PlaceLong Beach, USA
Abstract

Semantic segmentation has achieved huge progress via adopting deep Fully Convolutional Networks (FCN). However, the performance of FCN based models severely rely on the amounts of pixel-level annotations which are expensive and time-consuming. To address this problem, it is a good choice to learn to segment with weak supervision from bounding boxes. How to make full use of the class-level and region-level supervisions from bounding boxes is the critical challenge for the weakly supervised learning task. In this paper, we first introduce a box-driven class-wise masking model (BCM) to remove irrelevant regions of each class. Moreover, based on the pixel-level segment proposal generated from the bounding box supervision, we could calculate the mean filling rates of each class to serve as an important prior cue, then we propose a filling rate guided adaptive loss (FR-Loss) to help the model ignore the wrongly labeled pixels in proposals. Unlike previous methods directly training models with the fixed individual segment proposals, our method can adjust the model learning with global statistical information. Thus it can help reduce the negative impacts from wrongly labeled proposals. We evaluate the proposed method on the challenging PASCAL VOC 2012 benchmark and compare with other methods. Extensive experimental results show that the proposed method is effective and achieves the state-of-the-art results.

Keyword弱监督分割
MOST Discipline Catalogue工学::控制科学与工程
Document Type会议论文
Identifierhttp://ir.ia.ac.cn/handle/173211/28370
Collection智能感知与计算研究中心
Corresponding AuthorSong, Chunfeng
Affiliation1.Center for Research on Intelligent Perception and Computing (CRIPAC),National Laboratory of Pattern Recognition (NLPR),Institute of Automation, Chinese Academy of Sciences (CASIA)
2.The University of Sydney, SenseTime Computer Vision Research Group, Australia
3.Center for Excellence in Brain Science and Intelligence Technology (CEBSIT)
4.Chinese Academy of Sciences - Artificial Intelligence Research (CAS-AIR)
5.University of Chinese Academy of Sciences (UCAS)
First Author AffilicationChinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
Corresponding Author AffilicationChinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
Recommended Citation
GB/T 7714
Song, Chunfeng,Huang, Yang,Ouyang, Wanli,et al. Box-driven Class-wise Region Masking and Filling Rate Guided Loss for Weakly Supervised Semantic Segmentation[C],2019.
Files in This Item: Download All
File Name/Size DocType Version Access License
Song_Box-Driven_WSSS(1395KB)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
[Song, Chunfeng]'s Articles
[Huang, Yang]'s Articles
[Ouyang, Wanli]'s Articles
Baidu academic
Similar articles in Baidu academic
[Song, Chunfeng]'s Articles
[Huang, Yang]'s Articles
[Ouyang, Wanli]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Song, Chunfeng]'s Articles
[Huang, Yang]'s Articles
[Ouyang, Wanli]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: Song_Box-Driven_WSSS_CVPR_2019_paper.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

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