Towards Building Robust DNN Applications: An Industrial Case Study of Evolutionary Data Augmentation
Data augmentation techniques that increase the amount of training data by adding realistic transformations are used in machine learning to improve the level of accuracy. Recent studies have demonstrated that data augmentation techniques improve the robustness of image classification models with open datasets; however, it has yet to be investigated whether these techniques are effective for industrial datasets. In this study, we investigate the feasibility of data augmentation techniques for industrial use. We evaluate data augmentation techniques in image classification and object detection tasks using an industrial in-house graphical user interface dataset. As the results indicate, the genetic algorithm-based data augmentation technique outperforms two random-based methods in terms of the robustness of the image classification model. In addition, through this evaluation and interviews with the developers, we learned following two lessons: data augmentation techniques should (1) maintain the training speed to avoid slowing the development and (2) include extensibility for a variety of tasks.
Wed 23 Sep Times are displayed in time zone: (UTC) Coordinated Universal Time
01:10 - 02:10: Software Engineering for AI (2) Research Papers / Industry Showcase at Kangaroo Chair(s): Aldeida AletiMonash University | |||
01:10 - 01:30 Talk | Audee: Automated Testing for Deep Learning Frameworks Research Papers Qianyu GuoCollege of Intelligence and Computing, Tianjin University, Xiaofei XieNanyang Technological University, Yi LiNanyang Technological University, Singapore, Xiaoyu ZhangXi'an Jiaotong University, Yang LiuNanyang Technological University, Singapore, Li XiaohongTianJin University, Chao ShenXi'an Jiaotong University | ||
01:30 - 01:50 Talk | Towards Interpreting Recurrent Neural Networks through Probabilistic Abstraction Research Papers Guoliang DongComputer College of Zhejiang University, Jingyi WangZhejiang University, Jun SunSingapore Management University, Yang ZhangZhejiang University, Xinyu WangZhejiang University, Dai TingHuawei International Pte Ltd, Jin Song DongNational University of Singapore, Xingen WangZhejiang University | ||
01:50 - 02:10 Talk | Towards Building Robust DNN Applications: An Industrial Case Study of Evolutionary Data Augmentation Industry Showcase Haruki YokoyamaFujitsu Laboratories Ltd., Satoshi OnoueFujitsu Ltd., Shinji KikuchiFujitsu Laboratories Ltd. |