Modular Multimodal Architecture for Document Classification

Code

• github.com/iamarjunchandra/LayoutLM-Form-Understanding---Sequence-Labeling
  pytorch★ 0
• github.com/microsoft/unilm/tree/master/layoutlm
  pytorch★ 0
• github.com/BordiaS/layoutlm
  pytorch★ 0

Abstract

Page classification is a crucial component to any document analysis system, allowing for complex branching control flows for different components of a given document. Utilizing both the visual and textual content of a page, the proposed method exceeds the current state-of-the-art performance on the RVL-CDIP benchmark at 93.03% test accuracy.

Tasks

Reproductions