DocTTT：基于元辅助学习的测试时训练用于手写文档识别
DocTTT: Test-Time Training for Handwritten Document Recognition Using Meta-Auxiliary Learning
AI总结：
本文提出DocTTT框架，通过结合元学习与自监督掩码自编码器的元辅助学习，在测试时训练模型适应特定输入，显著提升复杂背景下手写文档识别的准确率。
摘要：
尽管手写文档识别（HDR）近期取得了显著进展，但在复杂背景、多样手写风格和不同文档布局下高效准确地识别文本仍然是一个实际挑战。此外，这个问题在学术研究中很少被解决，尤其是在可用标注数据极少的情况下。本文中，我们引入了DocTTT框架来解决这些挑战。我们方法的关键创新在于，它利用测试时训练来在测试阶段使模型适应每个特定输入。我们提出了一种新颖的元辅助学习方法，结合了元学习和自监督掩码自编码器（MAE）。在测试时，我们使用自监督MAE损失来调整视觉表示参数。在训练时，我们使用元学习框架学习模型参数，使得模型参数被学习为能有效适应新输入。实验结果表明，我们提出的方法在基准数据集上显著优于现有最先进的方法。
英文摘要：
Despite recent significant advancements in Handwritten Document Recognition (HDR), the efficient and accurate recognition of text against complex backgrounds, diverse handwriting styles, and varying document layouts remains a practical challenge. Moreover, this issue is seldom addressed in academic research, particularly in scenarios with minimal annotated data available. In this paper, we introduce the DocTTT framework to address these challenges. The key innovation of our approach is that it uses test-time training to adapt the model to each specific input during testing. We propose a novel Meta-Auxiliary learning approach that combines Meta-learning and self-supervised Masked Autoencoder~(MAE). During testing, we adapt the visual representation parameters using a self-supervised MAE loss. During training, we learn the model parameters using a meta-learning framework, so that the model parameters are learned to adapt to a new input effectively. Experimental results show that our proposed method significantly outperforms existing state-of-the-art approaches on benchmark datasets.
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。
