Uncertainty Guided Ensemble Self-Training for Semi-Supervised Global Field Reconstruction
This addresses the high cost of labeled data for field reconstruction in aerospace engineering, though it appears incremental as it builds on existing self-training methods.
The paper tackles the problem of reconstructing complex physics fields from limited sensor data in aerospace engineering by proposing Uncertainty Guided Ensemble Self-Training (UGE-ST), which uses unlabeled data to achieve the same accuracy as supervised learning while saving up to 90% of the data.
Recovering a globally accurate complex physics field from limited sensor is critical to the measurement and control in the aerospace engineering. General reconstruction methods for recovering the field, especially the deep learning with more parameters and better representational ability, usually require large amounts of labeled data which is unaffordable. To solve the problem, this paper proposes Uncertainty Guided Ensemble Self-Training (UGE-ST), using plentiful unlabeled data to improve reconstruction performance. A novel self-training framework with the ensemble teacher and pretraining student designed to improve the accuracy of the pseudo-label and remedy the impact of noise is first proposed. On the other hand, uncertainty-guided learning is proposed to encourage the model to focus on the highly confident regions of pseudo-labels and mitigate the effects of wrong pseudo-labeling in self-training, improving the performance of the reconstruction model. Experiments include the pressure velocity field reconstruction of airfoil and the temperature field reconstruction of aircraft system indicate that our UGE-ST can save up to 90% of the data with the same accuracy as supervised learning.