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.

翻译：深度神经网络在各类任务中展现出卓越性能，但其缺乏鲁棒性、可靠性且易过度自信的特点，为其在自动驾驶等安全关键领域的部署带来挑战。为此，量化模型预测中固有的不确定性是解决上述问题的有效途径。本文提出一种新颖的不确定性感知交叉熵损失（U-CE），通过对经典交叉熵损失进行像素级加权，将动态预测不确定性融入训练过程。通过在Cityscapes和ACDC两个基准数据集上、基于ResNet-18和ResNet-101两种常见骨干架构的广泛实验，我们证明了U-CE相较于常规CE训练的优势。采用U-CE训练的模型不仅提升了分割性能，还能在训练后提供有意义的不确定性结果。因此，本研究为开发更鲁棒、更可靠的分割模型做出了贡献，推动了安全关键领域及更广泛研究方向的发展。