Decoupled Attention Network for Text Recognition

  • Tianwei Wang South China University of Technology
  • Yuanzhi Zhu South China University of Technology
  • Lianwen Jin South China University of Technology
  • Canjie Luo South China University of Technology
  • Xiaoxue Chen South China University of Technology
  • Yaqiang Wu Lenovo Research
  • Qianying Wang Lenovo Research
  • Mingxiang Cai Lenovo Research

Abstract

Text recognition has attracted considerable research interests because of its various applications. The cutting-edge text recognition methods are based on attention mechanisms. However, most of attention methods usually suffer from serious alignment problem due to its recurrency alignment operation, where the alignment relies on historical decoding results. To remedy this issue, we propose a decoupled attention network (DAN), which decouples the alignment operation from using historical decoding results. DAN is an effective, flexible and robust end-to-end text recognizer, which consists of three components: 1) a feature encoder that extracts visual features from the input image; 2) a convolutional alignment module that performs the alignment operation based on visual features from the encoder; and 3) a decoupled text decoder that makes final prediction by jointly using the feature map and attention maps. Experimental results show that DAN achieves state-of-the-art performance on multiple text recognition tasks, including offline handwritten text recognition and regular/irregular scene text recognition. Codes will be released.1

Published
2020-04-03
Section
AAAI Technical Track: Vision