GuidedMix-Net: Semi-Supervised Semantic Segmentation by Using Labeled Images as Reference

Peng Tu1,2; Yawen Huang3; Feng Zheng1; Zhenyu He4; Liujuan Cao5; Ling Shao6

2022

36th AAAI Conference on Artificial Intelligence / 34th Conference on Innovative Applications of Artificial Intelligence / 12th Symposium on Educational Advances in Artificial Intelligence

2159-5399

2374-3468

THIRTY-SIXTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE / THIRTY-FOURTH CONFERENCE ON INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE / THE TWELVETH SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE

FEB 22-MAR 01, 2022

null,null,ELECTR NETWORK

2275 E BAYSHORE RD, STE 160, PALO ALTO, CA 94303 USA

ASSOC ADVANCEMENT ARTIFICIAL INTELLIGENCE

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.

第一 ; 通讯

英语

CPCI-S

National Natural Science Foundation of China["61972188","62122035"]

Computer Science

Computer Science, Artificial Intelligence

WOS:000893636202051

Web of Science

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

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.