Deep neural networks for scene perception in automated vehicles achieve excellent results for the domains they were trained on. However, in real-world conditions, the domain of operation and its underlying data distribution are subject to change. Adverse weather conditions, in particular, can significantly decrease model performance when such data are not available during training.Additionally, when a model is incrementally adapted to a new domain, it suffers from catastrophic forgetting, causing a significant drop in performance on previously observed domains. Despite recent progress in reducing catastrophic forgetting, its causes and effects remain obscure. Therefore, we study how the representations of semantic segmentation models are affected during domain-incremental learning in adverse weather conditions. Our experiments and representational analyses indicate that catastrophic forgetting is primarily caused by changes to low-level features in domain-incremental learning and that learning more general features on the source domain using pre-training and image augmentations leads to efficient feature reuse in subsequent tasks, which drastically reduces catastrophic forgetting. These findings highlight the importance of methods that facilitate generalized features for effective continual learning algorithms.

翻译：用于自动驾驶车辆场景感知的深度神经网络在训练领域取得了优异成果。然而，在实际环境中，运行领域及其底层数据分布会发生变化。特别是不利天气条件，当训练数据缺失时，会显著降低模型性能。此外，当模型逐步适应新领域时，会遭受灾难性遗忘，导致先前观测领域性能大幅下降。尽管近期在缓解灾难性遗忘方面取得进展，但其成因与影响仍不明确。为此，我们研究了不利天气条件下域增量学习过程中语义分割模型表示的变化规律。实验与表征分析表明：灾难性遗忘主要由域增量学习中低级特征变化引起；而通过预训练和数据增强在源领域学习更通用特征，可在后续任务中实现高效特征复用，从而显著抑制灾难性遗忘。这些发现凸显了促进特征通用化方法对构建高效持续学习算法的重要性。