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 2503.07079cs.SEcs.AI
收藏

深度神经网络模型无回归修复的经验报告

An Experience Report on Regression-Free Repair of Deep Neural Network Model

Fujitsu Limited(富士通公司);National Institute of Informatics(情报学研究所)

Takao Nakagawa, Susumu Tokumoto, Shogo Tokui, Fuyuki Ishikawa

AI总结:

本文报告了工业场景下DNN更新中的回归抑制问题,并通过基于NeuRecover定制目标函数,在富士通汽车图像安全应用上实现了特定类别无回归的模型更新。

摘要:

基于深度神经网络(DNN)的系统在工业界的使用日益广泛。在系统运行过程中,DNN需要被更新以提升其性能。当更新DNN时,要求高可靠性的公司所使用的系统必须尽可能减少回归。由于DNN的更新具有数据驱动的特性,开发者很难按预期抑制回归。本文识别了工业界中DNN更新的需求,并展示了一个使用相关技术来满足这些需求的案例研究。在该案例研究中,我们致力于满足这样一个需求:在不针对特定类别产生回归的前提下,更新在富士通收集的、假定用于安全应用的汽车图像上训练的模型。我们通过基于DNN修复技术NeuRecover定制目标函数,成功抑制了回归。此外,我们还讨论了案例研究中发现的一些挑战。

英文摘要:

Systems based on Deep Neural Networks (DNNs) are increasingly being used in industry. In the process of system operation, DNNs need to be updated in order to improve their performance. When updating DNNs, systems used in companies that require high reliability must have as few regressions as possible. Since the update of DNNs has a data-driven nature, it is difficult to suppress regressions as expected by developers. This paper identifies the requirements for DNN updating in industry and presents a case study using techniques to meet those requirements. In the case study, we worked on satisfying the requirement to update models trained on car images collected in Fujitsu assuming security applications without regression for a specific class. We were able to suppress regression by customizing the objective function based on NeuRecover, a DNN repair technique. Moreover, we discuss some of the challenges identified in the case study.

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。

↑