DocFusion: A Unified Framework for Document Parsing Tasks
This addresses the complexity and maintenance overhead in document parsing for downstream applications, though it appears incremental as a unified framework.
The paper tackles the problem of document parsing requiring multiple independent models by proposing DocFusion, a lightweight generative model with 0.28B parameters that unifies task representations. It achieves state-of-the-art performance across four key tasks through collaborative training and leveraging interactions among recognition tasks.
Document parsing is essential for analyzing complex document structures and extracting fine-grained information, supporting numerous downstream applications. However, existing methods often require integrating multiple independent models to handle various parsing tasks, leading to high complexity and maintenance overhead. To address this, we propose DocFusion, a lightweight generative model with only 0.28B parameters. It unifies task representations and achieves collaborative training through an improved objective function. Experiments reveal and leverage the mutually beneficial interaction among recognition tasks, and integrating recognition data significantly enhances detection performance. The final results demonstrate that DocFusion achieves state-of-the-art (SOTA) performance across four key tasks.