Revisiting Edge Detection in Convolutional Neural Networks

Revisiting Edge Detection in Convolutional Neural Networks

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.

回顾卷积神经网络中的边缘检测

检测边缘的能力是真正捕捉视觉概念所必需的基本属性。在本文中，我们证明了边缘无法在神经网络的第一卷积层中正确表示，并且进一步表明它们在流行的神经网络体系结构（如VGG-16和ResNet）中无法很好地捕获。.. 神经网络被发现依赖于颜色信息，可能在使用对自己的评价数据集的外意想不到的方式有所不同。为了提高它们的鲁棒性，我们提出了边缘检测单元，并表明它们减少了性能损失并生成了质量上不同的表示。通过比较各种模型，我们表明边缘检测的鲁棒性是有助于模型抵御色彩噪声的鲁棒性的重要因素。 （阅读更多）