| Title | GuidedMix-Net: Semi-Supervised Semantic Segmentation by Using Labeled Images as Reference |
| Author | |
| Corresponding Author | Feng Zheng |
| Publication Years | 2022
|
| Conference Name | 36th AAAI Conference on Artificial Intelligence / 34th Conference on Innovative Applications of Artificial Intelligence / 12th Symposium on Educational Advances in Artificial Intelligence
|
| ISSN | 2159-5399
|
| EISSN | 2374-3468
|
| Source Title | |
| Conference Date | FEB 22-MAR 01, 2022
|
| Conference Place | null,null,ELECTR NETWORK
|
| Publication Place | 2275 E BAYSHORE RD, STE 160, PALO ALTO, CA 94303 USA
|
| Publisher | |
| Abstract | Semi-supervised learning is a challenging problem which aims to construct a model by learning from limited labeled examples. Numerous methods for this task focus on utilizing the predictions of unlabeled instances consistency alone to regularize networks. However, treating labeled and unlabeled data separately often leads to the discarding of mass prior knowledge learned from the labeled examples. In this paper, we propose a novel method for semi-supervised semantic segmentation named GuidedMix-Net, by leveraging labeled information to guide the learning of unlabeled instances. Specifically, GuidedMix-Net employs three operations: 1) interpolation of similar labeled-unlabeled image pairs; 2) transfer of mutual information; 3) generalization of pseudo masks. It enables segmentation models can learning the higher-quality pseudo masks of unlabeled data by transfer the knowledge from labeled samples to unlabeled data. Along with supervised learning for labeled data, the prediction of unlabeled data is jointly learned with the generated pseudo masks from the mixed data. Extensive experiments on PASCAL VOC 2012, and Cityscapes demonstrate the effectiveness of our GuidedMix-Net, which achieves competitive segmentation accuracy and significantly improves the mIoU over 7% compared to previous approaches. |
| SUSTech Authorship | First
; Corresponding
|
| Language | English
|
| URL | [Source Record] |
| Indexed By | |
| Funding Project | National Natural Science Foundation of China["61972188","62122035"]
|
| WOS Research Area | Computer Science
|
| WOS Subject | Computer Science, Artificial Intelligence
|
| WOS Accession No | WOS:000893636202051
|
| Data Source | Web of Science
|
| Citation statistics |
Cited Times [WOS]:2
|
| Document Type | Conference paper |
| Identifier | http://kc.sustech.edu.cn/handle/2SGJ60CL/415790 |
| Department | Department of Computer Science and Engineering |
| Affiliation | 1.Southern University of Science and Technology, China 2.Shenzhen Microbt Electronics Technology Co., Ltd, China 3.Tencent Jarvis Lab, Shenzhen, China 4.Harbin Institute of Technology, Shenzhen, China 5.Xiamen University, Xiamen, China 6.National Center for Artificial Intelligence, Saudi Data and Artificial Intelligence Authority, Riyadh, Saudi Arabia |
| First Author Affilication | Southern University of Science and Technology |
| Corresponding Author Affilication | Southern University of Science and Technology |
| First Author's First Affilication | Southern University of Science and Technology |
| Recommended Citation GB/T 7714 |
Peng Tu,Yawen Huang,Feng Zheng,et al. GuidedMix-Net: Semi-Supervised Semantic Segmentation by Using Labeled Images as Reference[C]. 2275 E BAYSHORE RD, STE 160, PALO ALTO, CA 94303 USA:ASSOC ADVANCEMENT ARTIFICIAL INTELLIGENCE,2022.
|
| Files in This Item: | There are no files associated with this item. | |||||
Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.
;
Edit Comment