Abstract
This paper introduces DONUT-hole, a sparse OCR-free visual document understanding (VDU) model that addresses the limitations of its predecessor model, dubbed DONUT. The DONUT model, leveraging a transformer architecture, overcoming the challenges of separate optical character recognition (OCR) and visual semantic understanding (VSU) components. However, its deployment in production environments and edge devices is hindered by high memory and computational demands, particularly in large-scale request services. To overcome these challenges, we propose an optimization strategy based on knowledge distillation and model pruning. Our paradigm to produce DONUT-hole, reduces the model denisty by 54\% while preserving performance. We also achieve a global representational similarity index between DONUT and DONUT-hole based on centered kernel alignment (CKA) metric of 0.79. Moreover, we evaluate the effectiveness of DONUT-hole in the document image key information extraction (KIE) task, highlighting its potential for developing more efficient VDU systems for logistic companies.
Abstract (translated)
本文介绍了一种名为DONUT-hole的稀疏OCR-免费视觉文档理解（VDU）模型，它克服了其前身的局限性，前名为DONUT。DONUT模型利用Transformer架构，克服了光学字符识别（OCR）和视觉语义理解（VSU）组件的挑战。然而，其在生产环境和边缘设备上的部署受到高内存和计算需求的限制，特别是在大规模请求服务中。为了克服这些挑战，我们提出了基于知识蒸馏和模型剪裁的优化策略。我们的基于中心卷积对齐（CKA）指标的范式将模型的密度减少了54\%。此外，我们还通过CKA指标评估了DONUT-hole在文档图像关键信息提取（KIE）任务中的有效性，强调了其在开发更高效的VDU系统方面的潜力，尤其是在对面向逻辑公司的公司。
URL
https://arxiv.org/abs/2311.05778
