Journal
NEUROCOMPUTING
Volume 508, Issue -, Pages 36-46Publisher
ELSEVIER
DOI: 10.1016/j.neucom.2022.08.052
Keywords
Semantic segmentation; Semi-supervised learning; Student-teacher networks
Categories
Funding
- Natural Science Foundation of Zhejiang Province [LGG20F020011]
- Ningbo Science and Technology Innovation Project [2022Z075, 2021Z126]
- National Natural Science Foundation of China [61901237, 62171244]
- Alibaba Innovative Research Program
- Ningbo Public Welfare Technology Plan [2021S024]
- Open Fund by Ningbo Institute of Materials Technology Engineering
- Chinese Academy of Sciences
Ask authors/readers for more resources
This study proposes a cross-teacher training framework with three modules, including a cross-teacher module, high-level contrastive learning module, and low-level contrastive learning module, to significantly improve traditional semi-supervised learning methods. Experimental results demonstrate that our framework outperforms state-of-the-art methods on benchmark datasets.
Convolutional neural networks can achieve remarkable performance in semantic segmentation tasks. However, such neural network approaches heavily rely on costly pixel-level annotation. Semi-supervised learning is a promising resolution to tackle this issue, but its performance still far falls behind the fully supervised counterpart. This work proposes a cross-teacher training framework with three modules that significantly improves traditional semi-supervised learning approaches. The core is a cross-teacher module, which could simultaneously reduce the coupling among peer networks and the error accumulation between teacher and student networks. In addition, we propose two complementary contrastive learning modules. The high-level module can transfer high-quality knowledge from labeled data to unlabeled ones and promote separation between classes in feature space. The low-level module can encourage low-quality features learning from the high-quality features among peer networks. In experiments, the cross-teacher module significantly improves the performance of traditional student-teacher approaches, and our framework outperforms state-of-the-art methods on benchmark datasets. (C) 2022 Elsevier B.V. All rights reserved.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available