End-to-end Document Recognition and Understanding with Dessurt

Code

• github.com/herobd/dessurt
  OfficialIn paperpytorch★ 62
• github.com/herobd/NAF_dataset
  none★ 38

Abstract

We introduce Dessurt, a relatively simple document understanding transformer capable of being fine-tuned on a greater variety of document tasks than prior methods. It receives a document image and task string as input and generates arbitrary text autoregressively as output. Because Dessurt is an end-to-end architecture that performs text recognition in addition to the document understanding, it does not require an external recognition model as prior methods do. Dessurt is a more flexible model than prior methods and is able to handle a variety of document domains and tasks. We show that this model is effective at 9 different dataset-task combinations.

Tasks

Benchmark Results

Reproductions