arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2303.09347cs.CV
收藏

CSSL-MHTR:用于可扩展多文字手写文本识别的持续自监督学习

CSSL-MHTR: Continual Self-Supervised Learning for Scalable Multi-script Handwritten Text Recognition

Marwa Dhiaf, Mohamed Ali Souibgui, Kai Wang, Yuyang Liu, Yousri Kessentini, Alicia Fornés, Ahmed Cheikh Rouhou

AI总结:

本文提出CSSL-MHTR框架,通过为每个任务添加adapters中间层并从前一模型高效蒸馏知识,首次将持续自监督学习应用于多文字手写文本识别,有效缓解灾难性遗忘,在计算和内存上均高效,并在English、Italian和Russian文字上达到SOTA。

摘要:

自监督学习近期已成为文档分析中的一种强大替代方案。这些方法现在能够学习高质量的图像表示,并克服需要大量标注数据的有监督方法的局限性。然而,这些方法无法以增量方式捕获新知识,即数据按顺序呈现给模型,而这更接近现实场景。在本文中,我们以序列识别为例,探索持续自监督学习的潜力,以缓解手写文本识别中的灾难性遗忘问题。我们的方法包括为每个任务添加称为 adapters 的中间层,并在学习当前任务时从先前的模型中高效地蒸馏知识。我们提出的框架在计算和内存复杂度上均十分高效。为了证明其有效性,我们通过将学习到的模型迁移到各种文本识别下游任务来评估我们的方法,包括 Latin 和非 Latin 文字。据我们所知,这是持续自监督学习在手写文本识别中的首次应用。我们在 English、Italian 和 Russian 文字上取得了最先进的性能,同时每个任务仅增加了少量参数。代码和训练好的模型将公开提供。

英文摘要:

Self-supervised learning has recently emerged as a strong alternative in document analysis. These approaches are now capable of learning high-quality image representations and overcoming the limitations of supervised methods, which require a large amount of labeled data. However, these methods are unable to capture new knowledge in an incremental fashion, where data is presented to the model sequentially, which is closer to the realistic scenario. In this paper, we explore the potential of continual self-supervised learning to alleviate the catastrophic forgetting problem in handwritten text recognition, as an example of sequence recognition. Our method consists in adding intermediate layers called adapters for each task, and efficiently distilling knowledge from the previous model while learning the current task. Our proposed framework is efficient in both computation and memory complexity. To demonstrate its effectiveness, we evaluate our method by transferring the learned model to diverse text recognition downstream tasks, including Latin and non-Latin scripts. As far as we know, this is the first application of continual self-supervised learning for handwritten text recognition. We attain state-of-the-art performance on English, Italian and Russian scripts, whilst adding only a few parameters per task. The code and trained models will be publicly available.

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。

↑