DeepRepair: Style-guided repairing for deep neural networks in the real-world operational environment

• Main Authors: YU, Bing, QI, Hua, QING, Guo, JUEFEI-XU, Felix, XIE, Xiaofei, MA, Lei, ZHAO, Jianjun
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2021
• Subjects: Training; Maintenance engineering; Software; Data models; Training data; Neurons; Games; Data augmentation; deep neural network (DNN) repairing; deep neural network; operational environment; OS and Networks; Software Engineering
• Online Access: https://ink.library.smu.edu.sg/sis_research/7051; https://ink.library.smu.edu.sg/context/sis_research/article/8054/viewcontent/camera_ready.pdf
• Institution: Singapore Management University

Deep neural networks (DNNs) are continuously expanding their application to various domains due to their high performance. 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 under the deployed operational environment while not harming their capability of handling normal or clean data with limited failure samples we can collect. In this article, we propose a style-guided data augmentation for repairing DNN in the operational environment, which learns and introduces the unknown failure patterns within the failure samples into the training data via the style transfer. 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 15 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. Our technique successfully repairs three convolutional neural networks and two recurrent neural networks with averaging 62.88% and 39.02% accuracy enhancements on the 15 failure patterns, respectively, achieving higher repairing performance than state-of-the-art repairing methods on the most failure patterns with even better accuracy on clean datasets.