Though current object detection models based on deep learning have achieved excellent results on many conventional benchmark datasets, their performance will dramatically decline on real-world images taken under extreme conditions. Existing methods either used image augmentation based on traditional image processing algorithms or applied customized and scene-limited image adaptation technologies for robust modeling. This study thus proposes a stylization data-driven neural-image-adaptive YOLO (SDNIA-YOLO), which improves the model's robustness by enhancing image quality adaptively and learning valuable information related to extreme weather conditions from images synthesized by neural style transfer (NST). Experiments show that the developed SDNIA-YOLOv3 achieves significant [email protected] improvements of at least 15% on the real-world foggy (RTTS) and lowlight (ExDark) test sets compared with the baseline model. Besides, the experiments also highlight the outstanding potential of stylization data in simulating extreme weather conditions. The developed SDNIA-YOLO remains excellent characteristics of the native YOLO to a great extent, such as end-to-end one-stage, data-driven, and fast.

翻译：尽管当前基于深度学习的目标检测模型在许多常规基准数据集上取得了优异结果，但其在极端条件下拍摄的真实世界图像上的性能会急剧下降。现有方法要么使用基于传统图像处理算法的图像增强技术，要么采用定制化且场景受限的图像自适应技术进行鲁棒建模。因此，本研究提出了一种风格化数据驱动的神经图像自适应YOLO模型（SDNIA-YOLO），该模型通过自适应增强图像质量，并从神经风格迁移（NST）合成的图像中学习与极端天气条件相关的有价值信息，从而提升模型的鲁棒性。实验表明，与基线模型相比，所开发的SDNIA-YOLOv3在真实世界雾天（RTTS）和低光照（ExDark）测试集上实现了至少15%的[email protected]显著提升。此外，实验也凸显了风格化数据在模拟极端天气条件方面的突出潜力。所开发的SDNIA-YOLO在很大程度上保留了原生YOLO的优良特性，例如端到端单阶段、数据驱动以及快速检测。