GTC: Guided Training of CTC towards Efficient and Accurate Scene Text Recognition


  • Wenyang Hu Nanyang Technological University
  • Xiaocong Cai SenseTime Group
  • Jun Hou SenseTime Group
  • Shuai Yi SenseTime Group
  • Zhiping Lin Nanyang Technological University



Connectionist Temporal Classification (CTC) and attention mechanism are two main approaches used in recent scene text recognition works. Compared with attention-based methods, CTC decoder has a much shorter inference time, yet a lower accuracy. To design an efficient and effective model, we propose the guided training of CTC (GTC), where CTC model learns a better alignment and feature representations from a more powerful attentional guidance. With the benefit of guided training, CTC model achieves robust and accurate prediction for both regular and irregular scene text while maintaining a fast inference speed. Moreover, to further leverage the potential of CTC decoder, a graph convolutional network (GCN) is proposed to learn the local correlations of extracted features. Extensive experiments on standard benchmarks demonstrate that our end-to-end model achieves a new state-of-the-art for regular and irregular scene text recognition and needs 6 times shorter inference time than attention-based methods.




How to Cite

Hu, W., Cai, X., Hou, J., Yi, S., & Lin, Z. (2020). GTC: Guided Training of CTC towards Efficient and Accurate Scene Text Recognition. Proceedings of the AAAI Conference on Artificial Intelligence, 34(07), 11005-11012.



AAAI Technical Track: Vision