Semi-supervision semantic segmentation with uncertainty-guided self cross supervision
This work addresses computational inefficiency and error propagation in semi-supervised segmentation, offering a more resource-efficient solution for medical or autonomous driving applications.
The paper tackles the issues of wrong pseudo labeling and high computational cost in semi-supervised segmentation by proposing an uncertainty-guided self cross supervision method, which achieves state-of-the-art performance while saving 40.5% and 49.1% in parameters and calculations.
As a powerful way of realizing semi-supervised segmentation, the cross supervision method learns cross consistency based on independent ensemble models using abundant unlabeled images. However, the wrong pseudo labeling information generated by cross supervision would confuse the training process and negatively affect the effectiveness of the segmentation model. Besides, the training process of ensemble models in such methods also multiplies the cost of computation resources and decreases the training efficiency. To solve these problems, we propose a novel cross supervision method, namely uncertainty-guided self cross supervision (USCS). In addition to ensemble models, we first design a multi-input multi-output (MIMO) segmentation model which can generate multiple outputs with shared model and consequently impose consistency over the outputs, saving the cost on parameters and calculations. On the other hand, we employ uncertainty as guided information to encourage the model to focus on the high confident regions of pseudo labels and mitigate the effects of wrong pseudo labeling in self cross supervision, improving the performance of the segmentation model. Extensive experiments show that our method achieves state-of-the-art performance while saving 40.5% and 49.1% cost on parameters and calculations.