Deep Tri-Training for Semi-Supervised Image Segmentation

Shan An1; Haogang Zhu1; Jiaao Zhang2; Junjie Ye3; Siliang Wang4; Jianqin Yin5; Hong Zhang6

2022

10.1109/LRA.2022.3185768

IEEE Robotics and Automation Letters   影响因子和分区

2377-3774

Semantic segmentation is of great value to autonomous driving and many robotic applications, while it highly depends on costly and time-consuming pixel-level annotation. To make full use of unlabeled data, this work proposes a deep tri-training framework (dubbed DTT) to utilize labeled along with unlabeled data for training in a semi-supervised manner. Concretely, in the DTT framework, three networks are initialized with the same structure but different parameters. The networks are optimized circularly, where one network is trained in each optimization step with the guidance of the other two networks. A simple yet effective voting mechanism is adopted to construct reliable training sets from unlabeled data for the training stage and fusing multi-experts prediction in the testing stage. Exhaustive experiments on Cityscapes and PASCAL VOC 2012 demonstrate that the proposed DTT realizes state-of-the-art performance in the semi-supervised segmentation task. The source code is made publicly available.

Object Detection Segmentation and Categorization Semantic Scene Understanding Deep learning for visual perception Deep Learning Methods

SCI ; EI

英语

其他

National Key R&D Program of China[2021ZD0140407] ; National Natural Science Foundation of China[U21A20523]

Robotics

Robotics

WOS:000835813000036

IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC

20222812348089

Computer vision ; Deep learning ; Job analysis ; Object detection ; Semantic Segmentation

Ergonomics and Human Factors Engineering:461.4 ; Data Processing and Image Processing:723.2 ; Artificial Intelligence:723.4 ; Computer Applications:723.5 ; Vision:741.2

Web of Science

1.State Key Laboratory of Software Development Environment, Beihang University, Beijing, China
2.International School of Information Science & Engnieering, Dalian University of Technology, Dalian, China
3.School of Mechanical Engineering, Tongji University, Shanghai, China
4.School of Computer Science, Northwestern Polytechnical University, Xi’an, China
5.School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China
6.Department of Electronic and Electrical Engineering, Southern University of Science and Technology, Shenzhen, China

Shan An,Haogang Zhu,Jiaao Zhang,et al. Deep Tri-Training for Semi-Supervised Image Segmentation[J]. IEEE Robotics and Automation Letters,2022,PP(99):1-8.

Shan An.,Haogang Zhu.,Jiaao Zhang.,Junjie Ye.,Siliang Wang.,...&Hong Zhang.(2022).Deep Tri-Training for Semi-Supervised Image Segmentation.IEEE Robotics and Automation Letters,PP(99),1-8.

Shan An,et al."Deep Tri-Training for Semi-Supervised Image Segmentation".IEEE Robotics and Automation Letters PP.99(2022):1-8.