From Two to One: A New Scene Text Recognizer with Visual Language Modeling Network
从二到一:一种新的基于视觉语言建模网络的场景文本识别器
2から1へ:視覚言語モデリングネットワークを備えた新しいシーンテキスト認識装置
2 부터 1 까지:새로운 시각 언어 모델 링 네트워크 를 바탕 으로 하 는 장면 텍스트 식별 기
De dos a uno: un nuevo identificador de texto de escena basado en la red de modelado de lenguaje visual
De deux à un: un nouvel identificateur de texte de scène basé sur un réseau de modélisation de langage visuel
от 2 до 1: новая модель, основанная на визуальном языке
In this paper, we abandon the dominant complex language model and rethink the linguistic learning process in the scene text recognition. Different from previous methods considering the visual and linguistic information in two separate structures, we propose a Visual Language Modeling Network (VisionLAN), which views the visual and linguistic information as a union by directly enduing the vision model with language capability. Specially, we introduce the text recognition of character-wise occluded feature maps in the training stage. Such operation guides the vision model to use not only the visual texture of characters, but also the linguistic information in visual context for recognition when the visual cues are confused (e.g. occlusion, noise, etc.).
As the linguistic information is acquired along with visual features without the need of extra language model, VisionLAN significantly improves the speed by 39% and adaptively considers the linguistic information to enhance the visual features for accurate recognition. Furthermore, an Occlusion Scene Text (OST) dataset is proposed to evaluate the performance on the case of missing character-wise visual cues. The state of-the-art results on several benchmarks prove our effectiveness.