基于不确定性度量的半监督语义分割方法

Uncertain cross pseudo supervision for semi-supervised semantic segmentation

基于深度学习算法的预测通常被盲目地认为是准确的,而这种劣势在半监督学习中更为明显.为了解决这个问题,本文引入了一种简单但有效的正则化方法,即不确定性交叉伪监督.该方法通过不同的参数初始化对双学生网络施加了一致性约束,并将一个学生输出的独热分割图用作伪标签来监督另一个学生.同时独热分割图之间的詹森-香农距离用来估计伪标签的不确定性.此外,本文还提出了一种不确定损失用于降低拥有高不确定性的伪标签所带来的损失项权重.实验结果表明,本文方法实现了最先进的半监督语义分割性能.

Predictions based on deep learning algorithms are often blindly assumed to be accurate,and this disadvantage is more pronounced in semi-supervised learning.To address this problem,the authors introduce a simple but effective regularization approach,termed uncertain cross pseudo supervision.The paper approach imposes the consistency constraint on dual student networks perturbed with different initialization,where the one-hot segmentation map,output from one student,is used as pseudo labels to supervise the other.Uncertainty of pseudo labels are estimated by calculating the Jensen-Shannon divergence between dual predictions.Furthermore,a novel loss,called uncertain loss,is introduced to down-weight the loss assigned to high-uncertainty pseudo labels.Extensive experiments show that the proposed method achieves the state-of-the-art semi-supervised segmentation performance.