论文标题
卷积神经网络中的边缘检测
Revisiting Edge Detection in Convolutional Neural Networks
论文作者
论文摘要
检测边缘的能力是真正捕获视觉概念的基本属性。在本文中，我们证明，在神经网络的第一个卷积层中，边缘无法正确表示，并进一步表明它们在流行的神经网络体系结构（例如VGG-16和Resnet）中被捕获不佳。发现神经网络依赖于颜色信息，这些信息可能以用于评估的数据集以外的意外方式有所不同。为了提高其鲁棒性，我们提出了边缘检测单元，并表明它们会降低性能损失并在质量上产生不同的表示。通过比较各种模型，我们表明边缘检测的鲁棒性是导致模型抗色噪声鲁棒性的重要因素。
The ability to detect edges is a fundamental attribute necessary to truly capture visual concepts. In this paper, we prove that edges cannot be represented properly in the first convolutional layer of a neural network, and further show that they are poorly captured in popular neural network architectures such as VGG-16 and ResNet. The neural networks are found to rely on color information, which might vary in unexpected ways outside of the datasets used for their evaluation. To improve their robustness, we propose edge-detection units and show that they reduce performance loss and generate qualitatively different representations. By comparing various models, we show that the robustness of edge detection is an important factor contributing to the robustness of models against color noise.
