Weaklier Supervised Semantic Segmentation With Only One Image Level Annotation per Category

被引:22
作者
Li, Xi [1 ]
Ma, Huimin [1 ]
Luo, Xiong [2 ]
机构
[1] Tsinghua Univ, Dept Elect Engn, Beijing 100084, Peoples R China
[2] Univ Sci & Technol Beijing, Sch Comp & Commun Engn, Beijing 100083, Peoples R China
基金
中国国家自然科学基金;
关键词
Weaklier supervision; semantic segmentation; dual-branch iterative learning; CLASSIFICATION; SALIENCY;
D O I
10.1109/TIP.2019.2930874
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Image semantic segmentation tasks and methods based on weakly supervised conditions have been proposed and achieve better and better performance in recent years. However, the purpose of these tasks is mainly to simplify the labeling work. In this paper, we establish a new and more challenging task condition: weaklier supervision with one image level annotation per category, which only provides prior knowledge that humans need to recognize new objects, and aims to achieve pixel-level object semantic understanding. In order to solve this problem, a three-stage semantic segmentation framework is put forward, which realizes image level, pixel level, and object common features learning from coarse to fine grade, and finally obtains semantic segmentation results with accurate and complete object regions. Researches on PASCAL VOC 2012 dataset demonstrates the effectiveness of the proposed method, which makes an obvious improvement compared to baselines. Based on fewer supervised information, the method also provides satisfactory performance compared to weakly supervised learning-based methods with complete image-level annotations.
引用
收藏
页码:128 / 141
页数:14
相关论文
共 50 条
[1]   SLIC Superpixels Compared to State-of-the-Art Superpixel Methods [J].
Achanta, Radhakrishna ;
Shaji, Appu ;
Smith, Kevin ;
Lucchi, Aurelien ;
Fua, Pascal ;
Suesstrunk, Sabine .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2012, 34 (11) :2274-2281
[2]  
[Anonymous], ARXIV151106881
[3]  
[Anonymous], 2018, ARXIV180310464
[4]  
[Anonymous], 2014, INT C LEARN REPR ICL
[5]  
[Anonymous], NIPS 2011
[6]  
[Anonymous], 2015, PROC CVPR IEEE
[7]  
[Anonymous], 2014, arXiv
[8]   Exploiting Depth From Single Monocular Images for Object Detection and Semantic Segmentation [J].
Cao, Yuanzhouhan ;
Shen, Chunhua ;
Shen, Heng Tao .
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2017, 26 (02) :836-846
[9]   DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs [J].
Chen, Liang-Chieh ;
Papandreou, George ;
Kokkinos, Iasonas ;
Murphy, Kevin ;
Yuille, Alan L. .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2018, 40 (04) :834-848
[10]  
Chen LB, 2017, IEEE INT SYMP NANO, P1, DOI 10.1109/NANOARCH.2017.8053709