当前位置:
X-MOL 学术
›
arXiv.cs.SE
›
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.)
DeepRepair: Style-Guided Repairing for DNNs in the Real-world Operational Environment
arXiv - CS - Software Engineering Pub Date : 2020-11-19 , DOI: arxiv-2011.09884 Bing Yu and Hua Qi and Qing Guo and Felix Juefei-Xu and Xiaofei Xie and Lei Ma and Jianjun Zhao
arXiv - CS - Software Engineering Pub Date : 2020-11-19 , DOI: arxiv-2011.09884 Bing Yu and Hua Qi and Qing Guo and Felix Juefei-Xu and Xiaofei Xie and Lei Ma and Jianjun Zhao
Deep neural networks (DNNs) are being widely applied for various real-world
applications across domains due to their high performance (e.g., high accuracy
on image classification). Nevertheless, a well-trained DNN after deployment
could oftentimes raise errors during practical use in the operational
environment due to the mismatching between distributions of the training
dataset and the potential unknown noise factors in the operational environment,
e.g., weather, blur, noise etc. Hence, it poses a rather important problem for
the DNNs' real-world applications: how to repair the deployed DNNs for
correcting the failure samples (i.e., incorrect prediction) under the deployed
operational environment while not harming their capability of handling normal
or clean data. The number of failure samples we can collect in practice, caused
by the noise factors in the operational environment, is often limited.
Therefore, It is rather challenging how to repair more similar failures based
on the limited failure samples we can collect. In this paper, we propose a style-guided data augmentation for repairing DNN
in the operational environment. We propose a style transfer method to learn and
introduce the unknown failure patterns within the failure data into the
training data via data augmentation. Moreover, we further propose the
clustering-based failure data generation for much more effective style-guided
data augmentation. We conduct a large-scale evaluation with fifteen degradation
factors that may happen in the real world and compare with four
state-of-the-art data augmentation methods and two DNN repairing methods,
demonstrating that our method can significantly enhance the deployed DNNs on
the corrupted data in the operational environment, and with even better
accuracy on clean datasets.
中文翻译:
DeepRepair:真实世界操作环境中 DNN 的样式引导修复
由于其高性能(例如,图像分类的高精度),深度神经网络 (DNN) 正被广泛应用于跨领域的各种实际应用。然而,由于训练数据集的分布与操作环境中潜在的未知噪声因素(例如天气、模糊、噪声等)之间的不匹配,部署后训练有素的 DNN 在操作环境中的实际使用过程中经常会引发错误。因此,它对 DNN 的实际应用提出了一个相当重要的问题:如何修复已部署的 DNN 以纠正已部署操作环境下的故障样本(即错误预测),同时又不损害其处理正常或干净数据的能力. 我们在实践中可以收集的失败样本的数量,由运行环境中的噪声因素引起的,往往是有限的。因此,如何基于我们可以收集的有限故障样本修复更多类似故障是相当具有挑战性的。在本文中,我们提出了一种风格引导的数据增强,用于在操作环境中修复 DNN。我们提出了一种风格迁移方法,通过数据增强来学习并将故障数据中的未知故障模式引入到训练数据中。此外,我们进一步提出了基于聚类的故障数据生成,以实现更有效的风格引导数据增强。我们对现实世界中可能发生的 15 种退化因素进行了大规模评估,并与四种最先进的数据增强方法和两种 DNN 修复方法进行了比较,
更新日期:2020-11-20
中文翻译:
DeepRepair:真实世界操作环境中 DNN 的样式引导修复
由于其高性能(例如,图像分类的高精度),深度神经网络 (DNN) 正被广泛应用于跨领域的各种实际应用。然而,由于训练数据集的分布与操作环境中潜在的未知噪声因素(例如天气、模糊、噪声等)之间的不匹配,部署后训练有素的 DNN 在操作环境中的实际使用过程中经常会引发错误。因此,它对 DNN 的实际应用提出了一个相当重要的问题:如何修复已部署的 DNN 以纠正已部署操作环境下的故障样本(即错误预测),同时又不损害其处理正常或干净数据的能力. 我们在实践中可以收集的失败样本的数量,由运行环境中的噪声因素引起的,往往是有限的。因此,如何基于我们可以收集的有限故障样本修复更多类似故障是相当具有挑战性的。在本文中,我们提出了一种风格引导的数据增强,用于在操作环境中修复 DNN。我们提出了一种风格迁移方法,通过数据增强来学习并将故障数据中的未知故障模式引入到训练数据中。此外,我们进一步提出了基于聚类的故障数据生成,以实现更有效的风格引导数据增强。我们对现实世界中可能发生的 15 种退化因素进行了大规模评估,并与四种最先进的数据增强方法和两种 DNN 修复方法进行了比较,