Previous robustness approaches for deep learning models such as data augmentation techniques via data transformation or adversarial training cannot capture real-world variations that preserve the semantics of the input, such as a change in lighting conditions. To bridge this gap, we present NaTra, an adversarial training scheme that is designed to improve the robustness of image classification algorithms. We target attributes of the input images that are independent of the class identification, and manipulate those attributes to mimic real-world natural transformations (NaTra) of the inputs, which are then used to augment the training dataset of the image classifier. Specifically, we apply \textit{Batch Inverse Encoding and Shifting} to map a batch of given images to corresponding disentangled latent codes of well-trained generative models. \textit{Latent Codes Expansion} is used to boost image reconstruction quality through the incorporation of extended feature maps. \textit{Unsupervised Attribute Directing and Manipulation} enables identification of the latent directions that correspond to specific attribute changes, and then produce interpretable manipulations of those attributes, thereby generating natural transformations to the input data. We demonstrate the efficacy of our scheme by utilizing the disentangled latent representations derived from well-trained GANs to mimic transformations of an image that are similar to real-world natural variations (such as lighting conditions or hairstyle), and train models to be invariant to these natural transformations. Extensive experiments show that our method improves generalization of classification models and increases its robustness to various real-world distortions
翻译:用于深层次学习模型(例如通过数据转换或对抗性培训进行的数据增强技术)的以往稳健性方法无法捕捉保存输入语义的真实世界变异,例如灯光条件的变化。 为了缩小这一差距,我们展示了NaTra, 这是一种旨在改进图像分类算法的稳健性的对抗性培训计划。 我们把输入图像的属性作为目标,而这种输入图像与阶级识别无关,并把这些属性用于模仿真实世界的自然变异(NaTra),然后用来加强图像分类师的培训数据集。 具体地说,我们应用了\tliit{Batchnatch Inversion Enverational and Shifting} 来绘制一系列给受良好训练的基因化模型的可解释性潜伏性代码。\textit{Latent Commissions 扩展} 用来通过纳入扩展的地貌图来提高图像重建质量。 \ text{unsuperviced Refrial transformations) 来识别与具体属性变化相符, 然后产生这些可解释性的一般变现的图, 从而从自然变型的自然变现到模拟变型的变形, 演示到变型的自然变型的图图, 演示到变型的自然变型的变型的变型的变型,通过不断的变式的变式的变式的变式的变式的自然变式的变式,通过不断的变式的变式的变制的变制数据。