深度学习模型再工程的挑战与实践:一项计算机视觉领域的案例研究
Challenges and Practices of Deep Learning Model Reengineering: A Case Study on Computer Vision
AI总结:
本研究从过程视角聚焦计算机视觉领域的深度学习模型再工程,通过缺陷分析与访谈梳理其流程、缺陷分布及挑战实践,提出新型再工程工作流,为相关标准化与工具开发指明方向。
摘要:
许多工程组织正在重新实现并扩展来自研究界的深度神经网络,我们将这一过程定义为深度学习模型再工程。深度学习模型再工程——即复用、复现、适配和增强前沿深度学习方法——面临诸多挑战,原因包括参考模型文档记录不足、需求不断变化,以及实现与测试的成本较高。此外,工程师个人可能缺乏软件工程专业知识,但团队必须结合运用软件工程与深度学习知识才能取得成功。此前的研究从“产品”视角审视深度学习系统,不考虑工程师的具体目的,仅考察项目中的缺陷。我们的研究则从“过程”视角聚焦再工程活动,专门针对参与再工程流程的工程师展开。\n我们的研究目标是理解深度学习模型再工程的特征与挑战。我们以计算机视觉领域为背景,针对这一现象开展了案例研究。研究结果基于两个数据源:开源再工程项目中报告的缺陷,以及对开源项目贡献者和某再工程团队负责人的访谈。研究结果描述了基于深度学习的计算机视觉技术如何被再工程,分析了该过程中的缺陷分布,并探讨了相关挑战与实践方法。结合定量与定性数据,我们提出了一种全新的再工程工作流。我们的发现为多个未来方向提供了参考,包括:衡量模型再工程中更多未知的方面;标准化工程实践以促进再工程;开发支持模型再工程与模型复用的工具。
英文摘要:
Many engineering organizations are reimplementing and extending deep neural networks from the research community. We describe this process as deep learning model reengineering. Deep learning model reengineering - reusing, reproducing, adapting, and enhancing state-of-the-art deep learning approaches - is challenging for reasons including under-documented reference models, changing requirements, and the cost of implementation and testing. In addition, individual engineers may lack expertise in software engineering, yet teams must apply knowledge of software engineering and deep learning to succeed. Prior work has examined on DL systems from a "product" view, examining defects from projects regardless of the engineers' purpose. Our study is focused on reengineering activities from a "process" view, and focuses on engineers specifically engaged in the reengineering process. Our goal is to understand the characteristics and challenges of deep learning model reengineering. We conducted a case study of this phenomenon, focusing on the context of computer vision. Our results draw from two data sources: defects reported in open-source reeengineering projects, and interviews conducted with open-source project contributors and the leaders of a reengineering team. Our results describe how deep learning-based computer vision techniques are reengineered, analyze the distribution of defects in this process, and discuss challenges and practices. Integrating our quantitative and qualitative data, we proposed a novel reengineering workflow. Our findings inform several future directions, including: measuring additional unknown aspects of model reengineering; standardizing engineering practices to facilitate reengineering; and developing tools to support model reengineering and model reuse.
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。