Key Laboratory of Advanced Design and Intelligent Computing, Ministry of Education, Dalian University, Dalian 116622, China.
School of Computer Science and Technology, Dalian University of Technology, Dalian 116024, China.
Comput Intell Neurosci. 2022 Oct 3;2022:8653692. doi: 10.1155/2022/8653692. eCollection 2022.
The semisupervised semantic segmentation method uses unlabeled data to effectively reduce the required labeled data, and the pseudo supervision performance is greatly influenced by pseudo labels. Therefore, we propose a semisupervised semantic segmentation method based on mutual correction learning, which effectively corrects the wrong convergence direction of pseudo supervision. The well-calibrated segmentation confidence maps are generated through the multiscale feature fusion attention mechanism module. More importantly, using internal knowledge, a mutual correction mechanism based on consistency regularization is proposed to correct the convergence direction of pseudo labels during cross pseudo supervision. The multiscale feature fusion attention mechanism module and mutual correction learning improve the accuracy of the entire learning process. Experiments show that the MIoU (mean intersection over union) reaches 75.32%, 77.80%, 78.95%, and 79.16% using 1/16, 1/8, 1/4, and 1/2 labeled data on PASCAL VOC 2012. The results show that the new approach achieves an advanced level.
半监督语义分割方法利用未标记的数据有效地减少了所需的标记数据，而伪监督的性能受伪标签的影响很大。因此，我们提出了一种基于相互纠正学习的半监督语义分割方法，有效地纠正了伪监督的错误收敛方向。通过多尺度特征融合注意力机制模块生成了校准良好的分割置信度图。更重要的是，利用内部知识，提出了一种基于一致性正则化的相互纠正机制，以在交叉伪监督期间纠正伪标签的收敛方向。多尺度特征融合注意力机制模块和相互纠正学习提高了整个学习过程的准确性。实验表明，在 PASCAL VOC 2012 上使用 1/16、1/8、1/4 和 1/2 标记数据时，MIoU（平均交并比）分别达到 75.32%、77.80%、78.95%和 79.16%。结果表明，新方法达到了先进水平。
