Deep neural networks have shown exceptional performance in various tasks, but
their lack of robustness, reliability, and tendency to be overconfident pose
challenges for their deployment in safety-critical applications like autonomous
driving. In this regard, quantifying the uncertainty inherent to a model's
prediction is a promising endeavour to address these shortcomings. In this
work, we present a novel Uncertainty-aware Cross-Entropy loss (U-CE) that
incorporates dynamic predictive uncertainties into the training process by
pixel-wise weighting of the well-known cross-entropy loss (CE). Through
extensive experimentation, we demonstrate the superiority of U-CE over regular
CE training on two benchmark datasets, Cityscapes and ACDC, using two common
backbone architectures, ResNet-18 and ResNet-101. With U-CE, we manage to train
models that not only improve their segmentation performance but also provide
meaningful uncertainties after training. Consequently, we contribute to the
development of more robust and reliable segmentation models, ultimately
advancing the state-of-the-art in safety-critical applications and beyond.

利用动态预测不确定性的像素权重加权 U-CE（Uncertainty-aware Cross-Entropy loss）训练方法在两个基准数据集上优于传统 CE（cross-entropy loss）训练方法，提高了安全关键应用中更稳健可靠的分割模型的性能和可信度。