MASTER: Multi-aspect non-local network for scene text recognition

Attention-based scene text recognizers have gained huge success, which leverages a more compact in-termediate representation to learn 1d-or 2d-attention by a RNN-based encoder-decoder architecture. However, such methods suffer from attention-drift problem because high similarity among encoded features leads to attention confusion under the RNN-based local attention mechanism. Moreover, RNN-based methods have low efficiency due to poor parallelization. To overcome these problems, we propose the MASTER, a self-attention based scene text recognizer that (1) not only encodes the input-output at-tention but also learns self-attention which encodes feature-feature and target-target relationships inside the encoder and decoder and (2) learns a more powerful and robust intermediate representation to spa-tial distortion, and (3) owns a great training efficiency because of high training parallelization and a high-speed inference because of an efficient memory-cache mechanism. Extensive experiments on var-ious benchmarks demonstrate the superior performance of our MASTER on both regular and irregular scene text. Pytorch code can be found at https://github.com/wenwenyu/MASTER-pytorch, and Tensorflow code can be found at https://github.com/jiangxiluning/MASTER-TF . (c) 2021 Elsevier Ltd. All rights reserved.