Focus Anywhere for Fine-grained Multi-page Document Understanding

TL;DR

This paper introduces Fox, a novel approach that enhances large vision-language models to perform fine-grained, multi-page document understanding by focusing attention on specific regions and integrating multiple visual vocabularies.

Contribution

The paper presents a new pipeline, hybrid data, and tuning strategy that significantly improves LVLMs' ability to understand multi-page documents at a fine-grained level without modifying model weights.

Findings

Fox outperforms existing models on fine-grained document tasks.

The approach enables focus anywhere in multi-page documents.

A new benchmark with 9 sub-tasks promotes further research.

Abstract

Modern LVLMs still struggle to achieve fine-grained document understanding, such as OCR/translation/caption for regions of interest to the user, tasks that require the context of the entire page, or even multiple pages. Accordingly, this paper proposes Fox, an effective pipeline, hybrid data, and tuning strategy, that catalyzes LVLMs to focus anywhere on single/multi-page documents. We introduce a novel task to boost the document understanding by making LVLMs focus attention on the document-level region, such as redefining full-page OCR as foreground focus. We employ multiple vision vocabularies to extract visual hybrid knowledge for interleaved document pages (e.g., a page containing a photo). Meanwhile, we render cross-vocabulary vision data as the catalyzer to achieve a full reaction of multiple visual vocabularies and in-document figure understanding. Further, without modifying the weights of multiple vision vocabularies, the above catalyzed fine-grained understanding capabilities can be efficiently tuned to multi-page documents, enabling the model to focus anywhere in both format-free and page-free manners. Besides, we build a benchmark including 9 fine-grained sub-tasks (e.g., region-level OCR/summary, color-guided OCR) to promote document analysis in the community. The experimental results verify the superiority of our model.