无需真实数据，让合成手写文本模型跨语言直接适配真实书写。
Zero-Shot Synthetic-to-Real Handwritten Text Recognition via Task Analogies
- 通过源语言中合成到真实的参数变化模式，学习可迁移的修正方法。
- 在五种语言上均超越仅用合成数据的基线，部分提升超15%。
- 适用于无相关真实样本的新语言，特别适合低资源场景研究者。
基于合成手写的书写识别模型通常难以泛化到真实文本，而现有适配方法仍需目标域的真实样本。本文解决完全零样本的合成到真实泛化问题，即目标语言无任何真实数据。方法是在一个或多个源语言中学习从合成到真实书写时模型参数的变化规律，并将该修正知识迁移到新目标语言。多源情况下，利用语言相似性加权融合各源贡献。在五种语言和六种架构上的实验表明，该方法持续优于仅使用合成数据的基线，且迁移效果惠及与源语言无关的语言。
原文摘要 · Abstract (English)
Handwritten Text Recognition (HTR) models trained on synthetic handwriting often struggle to generalize to real text, and existing adaptation methods still require real samples from the target domain. In this work, we tackle the fully zero-shot synthetic-to-real generalization setting, where no real data from the target language is available. Our approach learns how model parameters change when moving from synthetic to real handwriting in one or more source languages and transfers this learned correction to new target languages. When using multiple sources, we rely on linguistic similarity to weigh their contrubition when combining them. Experiments across five languages and six architectures show consistent improvements over synthetic-only baselines and reveal that the transferred corrections benefit even languages unrelated to the sources.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。