Implicit Feature Alignment: Learn to Convert Text Recognizer to Text Spotter

TL;DR

This paper introduces Implicit Feature Alignment (IFA), a novel method that enables standard text recognizers to process multi-line text without relying on text detection, achieving state-of-the-art results in document recognition.

Contribution

The paper proposes IFA, a new inference paradigm that integrates into existing recognizers, allowing them to handle multi-line text and improve OCR performance.

Findings

State-of-the-art end-to-end document recognition performance

Fast inference speed maintained

Effective integration of IFA with attention-based and CTC-based recognizers

Abstract

Text recognition is a popular research subject with many associated challenges. Despite the considerable progress made in recent years, the text recognition task itself is still constrained to solve the problem of reading cropped line text images and serves as a subtask of optical character recognition (OCR) systems. As a result, the final text recognition result is limited by the performance of the text detector. In this paper, we propose a simple, elegant and effective paradigm called Implicit Feature Alignment (IFA), which can be easily integrated into current text recognizers, resulting in a novel inference mechanism called IFAinference. This enables an ordinary text recognizer to process multi-line text such that text detection can be completely freed. Specifically, we integrate IFA into the two most prevailing text recognition streams (attention-based and CTC-based) and propose attention-guided dense prediction (ADP) and Extended CTC (ExCTC). Furthermore, the Wasserstein-based Hollow Aggregation Cross-Entropy (WH-ACE) is proposed to suppress negative predictions to assist in training ADP and ExCTC. We experimentally demonstrate that IFA achieves state-of-the-art performance on end-to-end document recognition tasks while maintaining the fastest speed, and ADP and ExCTC complement each other on the perspective of different application scenarios. Code will be available at https://github.com/WangTianwei/Implicit-feature-alignment.