论文标题
一种使神经网络与多样化图像腐败进行强大的简单方法
A simple way to make neural networks robust against diverse image corruptions
论文作者
论文摘要
人类的视觉系统非常强大，与雨或雪等自然发生的各种自然变化和腐败。相比之下，现代图像识别模型的性能在对以前看不见的腐败进行评估时会大大降低。在这里，我们证明了一种简单但正确的调整训练，加上高斯和斑点噪声非常出人意料地概括了看不见的腐败，很容易在腐败基准Imagenet-c（带有resnet50）和mnist-c上达到先前的艺术状态。我们以这些强大的基线结果为基础，并表明对不相关的最坏情况噪声分布的识别模型进行对抗性训练会导致性能的额外提高。该正则化可以与先前提出的防御方法结合使用，以进一步改进。
The human visual system is remarkably robust against a wide range of naturally occurring variations and corruptions like rain or snow. In contrast, the performance of modern image recognition models strongly degrades when evaluated on previously unseen corruptions. Here, we demonstrate that a simple but properly tuned training with additive Gaussian and Speckle noise generalizes surprisingly well to unseen corruptions, easily reaching the previous state of the art on the corruption benchmark ImageNet-C (with ResNet50) and on MNIST-C. We build on top of these strong baseline results and show that an adversarial training of the recognition model against uncorrelated worst-case noise distributions leads to an additional increase in performance. This regularization can be combined with previously proposed defense methods for further improvement.
