NRTR: A No-Recurrence Sequence-to-Sequence Model For Scene Text Recognition
arXiv:1806.00926
Abstract
Scene text recognition has attracted a great many researches due to its importance to various applications. Existing methods mainly adopt recurrence or convolution based networks. Though have obtained good performance, these methods still suffer from two limitations: slow training speed due to the internal recurrence of RNNs, and high complexity due to stacked convolutional layers for long-term feature extraction. This paper, for the first time, proposes a no-recurrence sequence-to-sequence text recognizer, named NRTR, that dispenses with recurrences and convolutions entirely. NRTR follows the encoder-decoder paradigm, where the encoder uses stacked self-attention to extract image features, and the decoder applies stacked self-attention to recognize texts based on encoder output. NRTR relies solely on self-attention mechanism thus could be trained with more parallelization and less complexity. Considering scene image has large variation in text and background, we further design a modality-transform block to effectively transform 2D input images to 1D sequences, combined with the encoder to extract more discriminative features. NRTR achieves state-of-the-art or highly competitive performance on both regular and irregular benchmarks, while requires only a small fraction of training time compared to the best model from the literature (at least 8 times faster).
arXiv comment6 pages, 3 figures, 3 tables
References in corpus (8)
- TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems
- Synthetic Data and Artificial Neural Networks for Natural Scene Text Recognition
- Focusing Attention: Towards Accurate Text Recognition in Natural Images
- End-to-End Text Recognition with Hybrid HMM Maxout Models
- Deep Structured Output Learning for Unconstrained Text Recognition
- Scene Text Recognition with Sliding Convolutional Character Models
- Reading Scene Text with Attention Convolutional Sequence Modeling
- Scene Text Recognition from Two-Dimensional Perspective