arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2209.02132cs.CV
收藏

缩放图像对深度神经网络鲁棒性的影响

Impact of Scaled Image on Robustness of Deep Neural Networks

University of Electronic Science and Technology of China(电子科技大学)

Chengyin Hu, Weiwen Shi

AI总结:

本文研究图像缩放对深度神经网络鲁棒性的影响,提出缩放失真数据集ImageNet-CS,发现缩放尺寸与准确率下降呈正相关,并证实Augmix等鲁棒训练技术能有效提升网络对缩放变换的鲁棒性。

摘要:

深度神经网络(DNNs)已广泛应用于图像分类、目标检测和分割等计算机视觉任务中。然而,最近的研究表明,它们对输入图像中的人工数字扰动或失真具有脆弱性。网络的准确性受到其训练数据集的数据分布的显著影响。对原始图像进行缩放会创建分布外数据,这使其成为一种可能欺骗网络的对抗性攻击。在这项工作中,我们通过将 ImageNet Challenge 数据集的一个子集缩放不同倍数,提出了一个缩放失真数据集 ImageNet-CS。我们工作的目的是研究缩放图像对先进 DNNs 性能的影响。我们在提出的 ImageNet-CS 上对几种最先进的深度神经网络架构进行了实验,结果显示缩放尺寸与准确率下降之间存在显著的正相关。此外,基于 ResNet50 架构,我们在提出的 ImageNet-CS 上展示了最近提出的鲁棒训练技术和策略(如 Augmix、Revisiting 和 Normalizer Free)的性能测试。实验结果表明,这些鲁棒训练技术能够提高网络对缩放变换的鲁棒性。

英文摘要:

Deep neural networks (DNNs) have been widely used in computer vision tasks like image classification, object detection and segmentation. Whereas recent studies have shown their vulnerability to manual digital perturbations or distortion in the input images. The accuracy of the networks is remarkably influenced by the data distribution of their training dataset. Scaling the raw images creates out-of-distribution data, which makes it a possible adversarial attack to fool the networks. In this work, we propose a Scaling-distortion dataset ImageNet-CS by Scaling a subset of the ImageNet Challenge dataset by different multiples. The aim of our work is to study the impact of scaled images on the performance of advanced DNNs. We perform experiments on several state-of-the-art deep neural network architectures on the proposed ImageNet-CS, and the results show a significant positive correlation between scaling size and accuracy decline. Moreover, based on ResNet50 architecture, we demonstrate some tests on the performance of recent proposed robust training techniques and strategies like Augmix, Revisiting and Normalizer Free on our proposed ImageNet-CS. Experiment results have shown that these robust training techniques can improve networks' robustness to scaling transformation.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑