NRTR: A No-Recurrence Sequence-to-Sequence Model For Scene Text Recognition

TL;DR

NRTR introduces a novel no-recurrence, self-attention based sequence-to-sequence model for scene text recognition, achieving state-of-the-art results with significantly faster training times by eliminating recurrence and convolution.

Contribution

The paper presents the first no-recurrence, self-attention based scene text recognizer, reducing complexity and training time while maintaining high accuracy.

Findings

Achieves state-of-the-art or competitive performance on benchmarks.

Requires at least 8 times less training time than previous models.

Effectively handles regular and irregular scene text.

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).