Edit model card


Multimodal (text + layout/format + image) pre-training for document AI

The documentation of this model in the Transformers library can be found here.

Microsoft Document AI | GitHub


LayoutLMv2 is an improved version of LayoutLM with new pre-training tasks to model the interaction among text, layout, and image in a single multi-modal framework. It outperforms strong baselines and achieves new state-of-the-art results on a wide variety of downstream visually-rich document understanding tasks, including , including FUNSD (0.7895 β†’ 0.8420), CORD (0.9493 β†’ 0.9601), SROIE (0.9524 β†’ 0.9781), Kleister-NDA (0.834 β†’ 0.852), RVL-CDIP (0.9443 β†’ 0.9564), and DocVQA (0.7295 β†’ 0.8672).

LayoutLMv2: Multi-modal Pre-training for Visually-Rich Document Understanding Yang Xu, Yiheng Xu, Tengchao Lv, Lei Cui, Furu Wei, Guoxin Wang, Yijuan Lu, Dinei Florencio, Cha Zhang, Wanxiang Che, Min Zhang, Lidong Zhou, ACL 2021

Downloads last month
Unable to determine this model’s pipeline type. Check the docs .

Spaces using microsoft/layoutlmv2-base-uncased 16

Collection including microsoft/layoutlmv2-base-uncased