发表机构
Centre de Visió per Computador; Universitat Autònoma de Barcelona; Computer Science Department（计算机视觉中心; 巴塞罗那自治大学; 计算机科学系）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文首次从任务、架构和微调策略三个维度综合评估文档分析中的分布式学习，证明去中心化能提升模型对分布外数据的鲁棒性和泛化能力，而非仅是隐私权衡。
AI 中文摘要
隐私已成为文档分析社区中日益重要的关注点，以至于在档案、政府机构和本地企业等许多环境中，自动化的采用受到法律和政策限制的约束。虽然联邦学习常被视为一种“必要的恶”，意味着以去中心化和隐私为代价换取不可避免的性能权衡，但许多先前的工作忽视了其在提高对分布外数据鲁棒性方面的潜力。在本文中，我们提出了“毫不道歉地分布式”，这是首个同时沿三个关键轴评估文档分析中分布式学习的综合研究：所处理的任务、所采用的架构以及所应用的微调策略。具体而言，我们展示了各种分布式训练方法如何增强跨多种任务（如表识别、手写识别和单词 spotting）的泛化能力，特别是在迁移学习阶段。我们的结果提供了强有力的证据，表明去中心化不仅仅是一种约束，更是提高真实世界文档分析场景中模型鲁棒性和适应性的宝贵机会。
英文摘要
Privacy has become an increasingly important concern in the Document Analysis community, to the extent that in many environments such as archives, governmental institutions, and local businesses, the adoption of automation is restricted by legal and policy constraints. While federated learning has often been regarded as a ``necessary evil'', implying an unavoidable performance trade-off in exchange for decentralization and privacy, many prior works overlook its potential to improve robustness to out-of-distribution data. In this paper, we present Unapologetically Distributed, the first comprehensive study evaluating distributed learning in Document Analysis along three key axes simultaneously: the tasks addressed, the architectures employed, and the fine-tuning strategies applied. Specifically, we demonstrate how various distributed training approaches enhance generalization capabilities across diverse tasks such as Table Recognition, handwriting recognition, and Word Spotting, particularly during transfer learning stages. Our results provide strong evidence that decentralization is not merely a constraint, but a valuable opportunity to improve model robustness and adaptability in real-world Document Analysis scenarios.
CommentsAccepted at BMVC2026
