论文标题
二元形态神经网络
Binary Morphological Neural Network
论文作者
论文摘要
在过去的十年中，卷积神经网络（CNN）构成了大多数计算机视觉任务的深度学习体系结构的基础。但是，它们不一定是最佳的。例如，已知数学形态更适合处理二进制图像。在这项工作中，我们创建了一个处理二进制输入和输出的形态神经网络。我们提出了他们的构造，灵感来自CNNS，是通过用侵蚀和扩张来代替卷积来制定适合此类图像的层。我们给出了可解释的理论结果，以了解所产生的学习网络是否确实是形态操作员。我们提出了有希望的实验结果，旨在学习基本的二进制运营商，并且我们已在线公开使用代码。
In the last ten years, Convolutional Neural Networks (CNNs) have formed the basis of deep-learning architectures for most computer vision tasks. However, they are not necessarily optimal. For example, mathematical morphology is known to be better suited to deal with binary images. In this work, we create a morphological neural network that handles binary inputs and outputs. We propose their construction inspired by CNNs to formulate layers adapted to such images by replacing convolutions with erosions and dilations. We give explainable theoretical results on whether or not the resulting learned networks are indeed morphological operators. We present promising experimental results designed to learn basic binary operators, and we have made our code publicly available online.
