3MVRD: Multimodal Multi-task Multi-teacher Visually-Rich Form Document Understanding
This work addresses the challenge of interpreting complex form documents, which is crucial for applications in document processing and automation, though it appears to be an incremental improvement over existing knowledge distillation methods.
The paper tackles the problem of understanding visually-rich form documents by proposing a multimodal, multi-task, multi-teacher knowledge distillation model that leverages token and entity representations at fine-grained and coarse-grained levels. The model consistently outperforms existing baselines on publicly available datasets, demonstrating its efficacy in handling complex form structures.
This paper presents a groundbreaking multimodal, multi-task, multi-teacher joint-grained knowledge distillation model for visually-rich form document understanding. The model is designed to leverage insights from both fine-grained and coarse-grained levels by facilitating a nuanced correlation between token and entity representations, addressing the complexities inherent in form documents. Additionally, we introduce new inter-grained and cross-grained loss functions to further refine diverse multi-teacher knowledge distillation transfer process, presenting distribution gaps and a harmonised understanding of form documents. Through a comprehensive evaluation across publicly available form document understanding datasets, our proposed model consistently outperforms existing baselines, showcasing its efficacy in handling the intricate structures and content of visually complex form documents.