Andrade-Loarca Héctor, Kutyniok Gitta, Öktem Ozan
Institut für Mathematik, Technische Universität Berlin, 10623 Berlin, Germany.
Fakultät Elektrotechnik und Informatik, Technische Universität Berlin, 10587 Berlin, Germany.
Proc Math Phys Eng Sci. 2020 Nov;476(2243):20190841. doi: 10.1098/rspa.2019.0841. Epub 2020 Nov 25.
Semantic edge detection has recently gained a lot of attention as an image-processing task, mainly because of its wide range of real-world applications. This is based on the fact that edges in images contain most of the semantic information. Semantic edge detection involves two tasks, namely pure edge detection and edge classification. Those are in fact fundamentally distinct in terms of the level of abstraction that each task requires. This fact is known as the distracted supervision paradox and limits the possible performance of a supervised model in semantic edge detection. In this work, we will present a novel hybrid method that is based on a combination of the model-based concept of shearlets, which provides probably optimally sparse approximations of a model class of images, and the data-driven method of a suitably designed convolutional neural network. We show that it avoids the distracted supervision paradox and achieves high performance in semantic edge detection. In addition, our approach requires significantly fewer parameters than a pure data-driven approach. Finally, we present several applications such as tomographic reconstruction and show that our approach significantly outperforms former methods, thereby also indicating the value of such hybrid methods for biomedical imaging.
语义边缘检测作为一项图像处理任务，近来备受关注，主要因其在现实世界中有广泛应用。这基于图像中的边缘包含了大部分语义信息这一事实。语义边缘检测涉及两项任务，即纯边缘检测和边缘分类。实际上，就每项任务所需的抽象层次而言，这两项任务有着根本区别。这一事实被称为注意力分散监督悖论，它限制了监督模型在语义边缘检测中的可能性能。在这项工作中，我们将提出一种新颖的混合方法，该方法基于剪切波的基于模型的概念（它能为一类图像模型提供可能最优的稀疏近似）与适当设计的卷积神经网络的数据驱动方法相结合。我们表明，该方法避免了注意力分散监督悖论，并在语义边缘检测中取得了高性能。此外，与纯数据驱动方法相比，我们的方法所需参数显著更少。最后，我们展示了诸如断层重建等几个应用，并表明我们的方法明显优于以前的方法，从而也表明了这种混合方法在生物医学成像中的价值。
