Abstract. To ease visual inspections of exterior aircraft fuselage, new technical approaches have been recently deployed. Automated unmanned aerial vehicles (UAVs) are now acquiring high-quality images of aircraft in order to perform offline analysis. At first, some acquisitions are annotated by human operators in order to provide a large dataset required to train machine learning methods, especially for critical defect detection. An intrinsic problem of this dataset is its extreme imbalance (i.e., there is an unequal distribution between classes). The rarest and most valuable samples represent few elements among thousands of annotated objects. Deep learning (DL)-only based approaches have proven to be very effective when a sufficient amount of data are available for each desired class, whereas few-shot learning (FSL)-dedicated methods (matching network, prototypical network, etc.) can learn from only few samples. In a previous work, those approaches were compared on our applicative case and it was demonstrated that combining DL model and prototypical neural network in a hybrid architecture improves the results. We extend this work by questioning the interface between models in such a hybrid architecture. We show that by carefully selecting the data from the well-represented class when using FSL techniques, it is possible to enhance the previously proposed solution.

中文翻译：

---

用于无人机获取的飞机机身图像的罕见缺陷分类的深度和原型神经网络的混合

摘要。为了简化外部飞机机身的目视检查，最近部署了新技术方法。自动无人机 (UAV) 现在正在获取飞机的高质量图像，以便进行离线分析。起初，一些采集由人工操作员注释，以提供训练机器学习方法所需的大型数据集，尤其是关键缺陷检测。这个数据集的一个内在问题是它的极端不平衡（即，类之间的分布不均）。最稀有和最有价值的样本代表了数千个带注释的对象中的少数元素。当每个所需类别有足够数量的数据可用时，仅基于深度学习 (DL) 的方法已被证明非常有效，而少样本学习 (FSL) 专用方法（匹配网络、原型网络等）只能从少数样本中学习。在之前的工作中，这些方法在我们的应用案例中进行了比较，并证明在混合架构中结合 DL 模型和原型神经网络可以改善结果。我们通过质疑这种混合架构中模型之间的接口来扩展这项工作。我们表明，通过在使用 FSL 技术时从代表性良好的类中仔细选择数据，可以增强先前提出的解决方案。我们通过质疑这种混合架构中模型之间的接口来扩展这项工作。我们表明，通过在使用 FSL 技术时从代表性良好的类中仔细选择数据，可以增强先前提出的解决方案。我们通过质疑这种混合架构中模型之间的接口来扩展这项工作。我们表明，通过在使用 FSL 技术时从代表性良好的类中仔细选择数据，可以增强先前提出的解决方案。