FormNetV2: Multimodal Graph Contrastive Learning for Form Document Information Extraction

TL;DR

FormNetV2 introduces a unified multimodal graph contrastive learning approach for form document understanding, achieving state-of-the-art results with a more efficient model by integrating visual and textual cues without complex multi-task tuning.

Contribution

It proposes a novel centralized contrastive learning strategy that unifies multimodal pre-training, simplifying the process and enhancing performance in form document information extraction.

Findings

Achieves new state-of-the-art on multiple benchmarks.

Uses targeted visual cues without separate image embedder.

Maintains a more compact model size.

Abstract

The recent advent of self-supervised pre-training techniques has led to a surge in the use of multimodal learning in form document understanding. However, existing approaches that extend the mask language modeling to other modalities require careful multi-task tuning, complex reconstruction target designs, or additional pre-training data. In FormNetV2, we introduce a centralized multimodal graph contrastive learning strategy to unify self-supervised pre-training for all modalities in one loss. The graph contrastive objective maximizes the agreement of multimodal representations, providing a natural interplay for all modalities without special customization. In addition, we extract image features within the bounding box that joins a pair of tokens connected by a graph edge, capturing more targeted visual cues without loading a sophisticated and separately pre-trained image embedder. FormNetV2 establishes new state-of-the-art performance on FUNSD, CORD, SROIE and Payment benchmarks with a more compact model size.