提出Meta-DAN模型，加速手写文档页级识别并提升上下文理解。
Meta-DAN: towards an efficient prediction strategy for page-level handwritten text recognition
- 用窗口化查询和多标记预测，一次处理多个字符，减少推理步骤。
- 在10个数据集上达到最优字符错误率，单页识别速度显著提升。
- 适合需要快速高精度文档识别的场景，如历史文献数字化。
近期文本识别技术推动了页面级识别范式转变，从多步分割方法转向端到端注意力机制。然而，传统的逐字符自回归解码导致预测时间过长：在现代GPU上处理单页图像需数秒。我们提出元文档注意力网络（Meta-DAN），一种新型解码策略，在降低预测时间的同时增强上下文建模能力。其核心包括两个组件：窗口化查询，可一次性处理多个Transformer查询，扩展对近未来内容的建模；多标记预测，每次查询输出多个标记而非仅一个。我们在10个完整手写文档数据集上评估该方法，平均字符错误率达到当前最优水平。源代码与训练权重已公开于https://github.com/FactoDeepLearning/meta_dan。
原文摘要 · Abstract (English)
Recent advances in text recognition led to a paradigm shift for page-level recognition, from multi-step segmentation-based approaches to end-to-end attention-based ones. However, the naïve character-level autoregressive decoding process results in long prediction times: it requires several seconds to process a single page image on a modern GPU. We propose the Meta Document Attention Network (Meta-DAN) as a novel decoding strategy to reduce the prediction time while enabling a better context modeling. It relies on two main components: windowed queries, to process several transformer queries altogether, enlarging the context modeling with near future; and multi-token predictions, whose goal is to predict several tokens per query instead of only the next one. We evaluate the proposed approach on 10 full-page handwritten datasets and demonstrate state-of-the-art results on average in terms of character error rate. Source code and weights of trained models are available at https://github.com/FactoDeepLearning/meta_dan.
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。