Read Like Humans: Autonomous, Bidirectional and Iterative Language Modeling for Scene Text Recognition

TL;DR

This paper introduces ABINet, a novel scene text recognition model that explicitly models language bidirectionally and iteratively, significantly improving recognition accuracy especially on low-quality images.

Contribution

The paper proposes ABINet, which incorporates explicit language modeling, bidirectional feature representation, and iterative correction, advancing scene text recognition beyond implicit, unidirectional, and noise-sensitive models.

Findings

Achieves state-of-the-art results on multiple benchmarks.

Excels in recognizing low-quality and noisy images.

Self-training enhances learning from unlabeled data.

Abstract

Linguistic knowledge is of great benefit to scene text recognition. However, how to effectively model linguistic rules in end-to-end deep networks remains a research challenge. In this paper, we argue that the limited capacity of language models comes from: 1) implicitly language modeling; 2) unidirectional feature representation; and 3) language model with noise input. Correspondingly, we propose an autonomous, bidirectional and iterative ABINet for scene text recognition. Firstly, the autonomous suggests to block gradient flow between vision and language models to enforce explicitly language modeling. Secondly, a novel bidirectional cloze network (BCN) as the language model is proposed based on bidirectional feature representation. Thirdly, we propose an execution manner of iterative correction for language model which can effectively alleviate the impact of noise input. Additionally, based on the ensemble of iterative predictions, we propose a self-training method which can learn from unlabeled images effectively. Extensive experiments indicate that ABINet has superiority on low-quality images and achieves state-of-the-art results on several mainstream benchmarks. Besides, the ABINet trained with ensemble self-training shows promising improvement in realizing human-level recognition. Code is available at https://github.com/FangShancheng/ABINet.