Platypus: A Generalized Specialist Model for Reading Text in Various Forms

TL;DR

Platypus is a unified model that effectively recognizes various forms of text from images, combining the strengths of specialist and generalist approaches for improved accuracy and efficiency.

Contribution

The paper introduces Platypus, a generalized specialist model that unifies multiple text reading tasks with high accuracy and efficiency, and provides a new dataset called Worms for training and evaluation.

Findings

Platypus outperforms existing models on standard benchmarks.

The Worms dataset enhances training for diverse text recognition.

Platypus achieves a balance of accuracy and efficiency in multi-form text reading.

Abstract

Reading text from images (either natural scenes or documents) has been a long-standing research topic for decades, due to the high technical challenge and wide application range. Previously, individual specialist models are developed to tackle the sub-tasks of text reading (e.g., scene text recognition, handwritten text recognition and mathematical expression recognition). However, such specialist models usually cannot effectively generalize across different sub-tasks. Recently, generalist models (such as GPT-4V), trained on tremendous data in a unified way, have shown enormous potential in reading text in various scenarios, but with the drawbacks of limited accuracy and low efficiency. In this work, we propose Platypus, a generalized specialist model for text reading. Specifically, Platypus combines the best of both worlds: being able to recognize text of various forms with a single unified architecture, while achieving excellent accuracy and high efficiency. To better exploit the advantage of Platypus, we also construct a text reading dataset (called Worms), the images of which are curated from previous datasets and partially re-labeled. Experiments on standard benchmarks demonstrate the effectiveness and superiority of the proposed Platypus model. Model and data will be made publicly available at https://github.com/AlibabaResearch/AdvancedLiterateMachinery/tree/main/OCR/Platypus.