Despite their renowned predictive power on i.i.d. data, convolutional neural networks are known to rely more on high-frequency patterns that humans deem superficial than on low-frequency patterns that agree better with intuitions about what constitutes category membership. This paper proposes a method for training robust convolutional networks by penalizing the predictive power of the local representations learned by earlier layers. Intuitively, our networks are forced to discard predictive signals such as color and texture that can be gleaned from local receptive fields and to rely instead on the global structures of the image. Across a battery of synthetic and benchmark domain adaptation tasks, our method confers improved generalization out of the domain. Also, to evaluate cross-domain transfer, we introduce ImageNet-Sketch, a new dataset consisting of sketch-like images, that matches the ImageNet classification validation set in categories and scale.

本文提出了一种训练且具有鲁棒性的卷积神经网络的方法，通过惩罚较早层所学习的局部表示的预测能力，迫使网络丢弃色彩和纹理等可从局部感受野中获取的预测信号，并依靠图像的全局结构。在一系列综合性和基准领域适应任务中，我们的方法使泛化能力得到了改善。我们还引入了一个新的数据集ImageNet-Sketch，以评估跨域传输。

通过惩罚局部预测能力学习稳健的全局表示