GTC: Guided Training of CTC Towards Efficient and Accurate Scene Text Recognition
This addresses the problem of efficient and accurate text recognition in real-world applications, offering a significant speed improvement while maintaining high accuracy, though it is an incremental advancement over existing CTC methods.
The paper tackles the trade-off between speed and accuracy in scene text recognition by proposing Guided Training of CTC (GTC), which uses attentional guidance to improve CTC models, achieving state-of-the-art accuracy on regular and irregular text benchmarks with 6 times faster inference than attention-based methods.
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 attentionbased methods.