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.
@article{arxiv.2305.02549,
title = {FormNetV2: Multimodal Graph Contrastive Learning for Form Document Information Extraction},
author = {Chen-Yu Lee and Chun-Liang Li and Hao Zhang and Timothy Dozat and Vincent Perot and Guolong Su and Xiang Zhang and Kihyuk Sohn and Nikolai Glushnev and Renshen Wang and Joshua Ainslie and Shangbang Long and Siyang Qin and Yasuhisa Fujii and Nan Hua and Tomas Pfister},
journal= {arXiv preprint arXiv:2305.02549},
year = {2023}
}