Abstract
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.
Abstract (translated)
尽管手写文档识别（HDR）领域近年来取得了显著进展，但在复杂背景、多样的书写风格和不同的文档布局下高效准确地识别文本仍然是一项实际挑战。此外，在学术研究中，尤其是在缺乏充足标注数据的情况下解决这些问题的尝试很少。在本文中，我们介绍了DocTTT框架来应对这些挑战。我们的方法的关键创新在于它使用测试时训练（test-time training）来自适应调整模型以针对每个特定输入进行优化。 具体而言，我们提出了一种新颖的元辅助学习方法，该方法结合了元学习和自监督掩码自动编码器（MAE）。在测试阶段，通过自监督的MAE损失函数来调整视觉表示参数。而在训练过程中，则利用一个元学习框架来学习模型参数，使模型能够在面对新输入时有效地进行适应。 实验结果表明，在基准数据集上，我们提出的方法显著优于现有的最先进的方法。
URL
https://arxiv.org/abs/2501.12898
