Deep learning has become in recent years a cornerstone tool fueling key innovations in the industry, such as autonomous driving. To attain good performances, the neural network architecture used for a given application must be chosen with care. These architectures are often handcrafted and therefore prone to human biases and sub-optimal selection. Neural Architecture Search (NAS) is a framework introduced to mitigate such risks by jointly optimizing the network architectures and its weights. Albeit its novelty, it was applied on complex tasks with significant results - e.g. semantic image segmentation. In this technical paper, we aim to evaluate its ability to tackle a challenging operational task: semantic segmentation of objects of interest in satellite imagery. Designing a NAS framework is not trivial and has strong dependencies to hardware constraints. We therefore motivate our NAS approach selection and provide corresponding implementation details. We also present novel ideas to carry out other such use-case studies.

翻译：近些年来,深层学习已成为推动行业关键创新,如自主驱动等的基石工具。为了取得良好的表现,必须谨慎地选择用于特定应用的神经网络结构。这些结构往往是手工制作的,因此容易受到人类偏见和次优选择的影响。神经结构搜索(NAS)是一个通过共同优化网络结构及其重量来减轻这种风险的框架。尽管它具有新颖性,但它被用于具有重要成果的复杂任务,例如语义图像分割。在本技术文件中,我们旨在评估其应对具有挑战性的业务任务的能力:卫星图像中感兴趣对象的语义分割。设计NAS框架并非微不足道,而且在很大程度上依赖硬件限制。因此,我们鼓励我们采用NAS方法选择,并提供相应的实施细节。我们还提出了开展其他此类使用案例研究的新想法。