Robust segmentation performance under dense fog is crucial for autonomous driving, but collecting labeled real foggy scene datasets is burdensome in the real world. To this end, existing methods have adapted models trained on labeled clear weather images to the unlabeled real foggy domain. However, these approaches require intermediate domain datasets (e.g. synthetic fog) and involve multi-stage training, making them cumbersome and less practical for real-world applications. In addition, the issue of overconfident pseudo-labels by a confidence score remains less explored in self-training for foggy scene adaptation. To resolve these issues, we propose a new framework, named DAEN, which Directly Adapts without additional datasets or multi-stage training and leverages an ENergy score in self-training. Notably, we integrate a High-order Style Matching (HSM) module into the network to match high-order statistics between clear weather features and real foggy features. HSM enables the network to implicitly learn complex fog distributions without relying on intermediate domain datasets or multi-stage training. Furthermore, we introduce Energy Score-based Pseudo-Labeling (ESPL) to mitigate the overconfidence issue of the confidence score in self-training. ESPL generates more reliable pseudo-labels through a pixel-wise energy score, thereby alleviating bias and preventing the model from assigning pseudo-labels exclusively to head classes. Extensive experiments demonstrate that DAEN achieves state-of-the-art performance on three real foggy scene datasets and exhibits a generalization ability to other adverse weather conditions. Code is available at https://github.com/jdg900/daen

中文翻译：

---

用于雾场景分割的无中间域数据集的基于能量的域自适应


在浓雾下保持稳健的分割性能对于自动驾驶至关重要，但在现实世界中收集标记的真实雾场景数据集是繁重的。为此，现有方法已在标记的晴朗天气图像上训练的模型适应未标记的真实雾域。然而，这些方法需要中间域数据集（例如合成雾）并涉及多阶段训练，这使得它们很麻烦，对于实际应用来说不太实用。此外，在雾景适应的自我训练中，由置信度分数过度自信的伪标签问题仍然较少被探索。为了解决这些问题，我们提出了一个名为 DAEN 的新框架，该框架无需额外的数据集或多阶段训练即可直接适应，并在自我训练中利用 ENergy 分数。值得注意的是，我们将高阶风格匹配 （HSM） 模块集成到网络中，以匹配晴朗天气特征和真实雾气特征之间的高阶统计数据。HSM 使网络能够隐式学习复杂的雾分布，而无需依赖中间域数据集或多阶段训练。此外，我们引入了基于能量评分的伪标签 （ESPL） 来缓解自我训练中置信度分数的过度自信问题。ESPL 通过像素级能量分数生成更可靠的伪标签，从而减轻偏差并防止模型将伪标签专门分配给头部类别。广泛的实验表明，DAEN 在三个真实的雾场景数据集上实现了最先进的性能，并表现出对其他恶劣天气条件的泛化能力。代码可在 https://github.com/jdg900/daen 获取