CASIA OpenIR  > 模式识别国家重点实验室  > 图像与视频分析
Dictionary learning based superpixels clustering for weakly-supervised semantic segmentation
Peng Ying; Jing Liu; Hanqing Lu
2015
Conference NameIEEE International Conference on Image Processing
Source Publication
Conference DateSeptember 27-30, 2016
Conference PlaceQuebec City, QC, Canada
Abstract
; The task of weakly-supervised semantic segmentation is solved by assigning image-level labels to over-segmented superpixels. Considering that superpixels are geometrically and semantically ambiguous for label assignment, we propose a joint solution of semantic segmentation to enhance the learnability of superpixels. First, our model includes a spectral clustering item and a discriminative clustering item to obtain some clustering subsets of superpixels (ideally semantic regions), which are more separable semantically than independent superpixels. Second, sparse coding based feature for superpixel is adopted to make the representation robust to noise, and the dictionary for the sparse representation is learned together with the above clustering items. Third, a weakly supervised item for superpixels, transferred from image-level labels, is attached. We jointly formulate the above problems as a non-convex objective function, and optimize it by the constraint concave-convex programming (CCCP) algorithm. Extensive experiments on MSRC-21 and LabelMe datasets prove the effectiveness of our approach.
KeywordDictionary Learning Weak Supervision Semantic Segmentation
Document Type会议论文
Identifierhttp://ir.ia.ac.cn/handle/173211/11600
Collection模式识别国家重点实验室_图像与视频分析
Corresponding AuthorJing Liu
Recommended Citation
GB/T 7714
Peng Ying,Jing Liu,Hanqing Lu. Dictionary learning based superpixels clustering for weakly-supervised semantic segmentation[C],2015.
Files in This Item: Download All
File Name/Size DocType Version Access License
应鹏_ICIP.pdf(1666KB)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
[Peng Ying]'s Articles
[Jing Liu]'s Articles
[Hanqing Lu]'s Articles
Baidu academic
Similar articles in Baidu academic
[Peng Ying]'s Articles
[Jing Liu]'s Articles
[Hanqing Lu]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Peng Ying]'s Articles
[Jing Liu]'s Articles
[Hanqing Lu]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: 应鹏_ICIP.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

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