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 2005.10247cs.LGcs.CVstat.ML
收藏

基于模型的鲁棒深度学习:推广到自然的、分布外的数据

Model-Based Robust Deep Learning: Generalizing to Natural, Out-of-Distribution Data

Department of Electrical and Systems Engineering University of Pennsylvania(宾夕法尼亚大学电气工程与系统工程系)

Alexander Robey, Hamed Hassani, George J. Pappas

摘要:

虽然深度学习在许多应用领域取得了重大突破,但深度学习中常用的框架仍然容易受到人工制作的数据变化的影响。为了应对这种脆弱性,对抗性训练已经成为增强深度学习对范数有界扰动的鲁棒性的原则性方法。然而,对于深度学习来说,还有其他一些脆弱性的来源,可以说是更常见的,也没有得到彻底的研究。事实上,自然变化(如照明或天气条件)会显著降低训练神经网络的准确性,证明这种自然变化对深度学习提出了重大挑战。在本文中,我们提出了从基于扰动的对抗鲁棒性到基于模型的鲁棒深度学习的范式转变。我们的目标是提供通用的训练算法,可用于训练深度神经网络,使其对数据的自然变化具有鲁棒性。我们的范例的关键是首先获得一个模型的自然变化,可用于改变数据在一系列的自然条件。这样的模型可以是先验已知的,或者是从数据中学习的。在后一种情况下,我们证明了深度生成模型可以用来学习与现实条件一致的自然变异模型。然后,我们在三种新的基于模型的鲁棒训练算法中利用这些模型,以增强深度学习对给定模型的鲁棒性。我们的大量实验表明,在各种自然发生的条件下和各种数据集上,使用我们基于模型的算法训练的深度神经网络的性能明显优于标准深度学习算法以及范数有界的鲁棒深度学习算法。

英文摘要:

While deep learning has resulted in major breakthroughs in many application domains, the frameworks commonly used in deep learning remain fragile to artificially-crafted and imperceptible changes in the data. In response to this fragility, adversarial training has emerged as a principled approach for enhancing the robustness of deep learning with respect to norm-bounded perturbations. However, there are other sources of fragility for deep learning that are arguably more common and less thoroughly studied. Indeed, natural variation such as lighting or weather conditions can significantly degrade the accuracy of trained neural networks, proving that such natural variation presents a significant challenge for deep learning. In this paper, we propose a paradigm shift from perturbation-based adversarial robustness toward model-based robust deep learning. Our objective is to provide general training algorithms that can be used to train deep neural networks to be robust against natural variation in data. Critical to our paradigm is first obtaining a model of natural variation which can be used to vary data over a range of natural conditions. Such models may be either known a priori or else learned from data. In the latter case, we show that deep generative models can be used to learn models of natural variation that are consistent with realistic conditions. We then exploit such models in three novel model-based robust training algorithms in order to enhance the robustness of deep learning with respect to the given model. Our extensive experiments show that across a variety of naturally-occurring conditions and across various datasets, deep neural networks trained with our model-based algorithms significantly outperform both standard deep learning algorithms as well as norm-bounded robust deep learning algorithms.

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。

↑