当前位置:
X-MOL 学术
›
arXiv.cs.LG
›
论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
A Little Fog for a Large Turn
arXiv - CS - Machine Learning Pub Date : 2020-01-16 , DOI: arxiv-2001.05873 Harshitha Machiraju, Vineeth N Balasubramanian
arXiv - CS - Machine Learning Pub Date : 2020-01-16 , DOI: arxiv-2001.05873 Harshitha Machiraju, Vineeth N Balasubramanian
Small, carefully crafted perturbations called adversarial perturbations can
easily fool neural networks. However, these perturbations are largely additive
and not naturally found. We turn our attention to the field of Autonomous
navigation wherein adverse weather conditions such as fog have a drastic effect
on the predictions of these systems. These weather conditions are capable of
acting like natural adversaries that can help in testing models. To this end,
we introduce a general notion of adversarial perturbations, which can be
created using generative models and provide a methodology inspired by
Cycle-Consistent Generative Adversarial Networks to generate adversarial
weather conditions for a given image. Our formulation and results show that
these images provide a suitable testbed for steering models used in Autonomous
navigation models. Our work also presents a more natural and general definition
of Adversarial perturbations based on Perceptual Similarity.
中文翻译:
大转弯的小雾
称为对抗性扰动的小而精心设计的扰动可以很容易地欺骗神经网络。然而,这些扰动在很大程度上是可加性的,并不是自然发现的。我们将注意力转向自主导航领域,其中雾等不利天气条件会对这些系统的预测产生巨大影响。这些天气条件能够像自然对手一样发挥作用,可以帮助测试模型。为此,我们引入了对抗性扰动的一般概念,它可以使用生成模型创建,并提供一种受周期一致生成对抗网络启发的方法,为给定图像生成对抗性天气条件。我们的公式和结果表明,这些图像为自主导航模型中使用的转向模型提供了合适的测试平台。
更新日期:2020-01-17
中文翻译:
大转弯的小雾
称为对抗性扰动的小而精心设计的扰动可以很容易地欺骗神经网络。然而,这些扰动在很大程度上是可加性的,并不是自然发现的。我们将注意力转向自主导航领域,其中雾等不利天气条件会对这些系统的预测产生巨大影响。这些天气条件能够像自然对手一样发挥作用,可以帮助测试模型。为此,我们引入了对抗性扰动的一般概念,它可以使用生成模型创建,并提供一种受周期一致生成对抗网络启发的方法,为给定图像生成对抗性天气条件。我们的公式和结果表明,这些图像为自主导航模型中使用的转向模型提供了合适的测试平台。