IPAD: Iterative, Parallel, and Diffusion-based Network for Scene Text Recognition
This work addresses the inference speed bottleneck in scene text recognition, which is crucial for real-time applications, though it is incremental in improving existing methods.
The paper tackles the trade-off between speed and accuracy in scene text recognition by proposing a parallel, iterative decoder with a diffusion strategy, achieving superior results on benchmark datasets for Chinese and English text.
Nowadays, scene text recognition has attracted more and more attention due to its diverse applications. Most state-of-the-art methods adopt an encoder-decoder framework with the attention mechanism, autoregressively generating text from left to right. Despite the convincing performance, this sequential decoding strategy constrains the inference speed. Conversely, non-autoregressive models provide faster, simultaneous predictions but often sacrifice accuracy. Although utilizing an explicit language model can improve performance, it burdens the computational load. Besides, separating linguistic knowledge from vision information may harm the final prediction. In this paper, we propose an alternative solution that uses a parallel and iterative decoder that adopts an easy-first decoding strategy. Furthermore, we regard text recognition as an image-based conditional text generation task and utilize the discrete diffusion strategy, ensuring exhaustive exploration of bidirectional contextual information. Extensive experiments demonstrate that the proposed approach achieves superior results on the benchmark datasets, including both Chinese and English text images.