Scene Text Recognition (STR) is a challenging task that involves recognizing text within images of natural scenes. Although current state-of-the-art models for STR exhibit high performance, they typically suffer from low inference efficiency due to their reliance on hybrid architectures comprised of visual encoders and sequence decoders. In this work, we propose the VIsion Permutable extractor for fast and efficient scene Text Recognition (VIPTR), which achieves an impressive balance between high performance and rapid inference speeds in the domain of STR. Specifically, VIPTR leverages a visual-semantic extractor with a pyramid structure, characterized by multiple self-attention layers, while eschewing the traditional sequence decoder. This design choice results in a lightweight and efficient model capable of handling inputs of varying sizes. Extensive experimental results on various standard datasets for both Chinese and English scene text recognition validate the superiority of VIPTR. Notably, the VIPTR-T (Tiny) variant delivers highly competitive accuracy on par with other lightweight models and achieves SOTA inference speeds. Meanwhile, the VIPTR-L (Large) variant attains greater recognition accuracy, while maintaining a low parameter count and favorable inference speed. Our proposed method provides a compelling solution for the STR challenge, which blends high accuracy with efficiency and greatly benefits real-world applications requiring fast and reliable text recognition. The code is publicly available at https://github.com/cxfyxl/VIPTR.

翻译：场景文本识别（STR）是一项具有挑战性的任务，涉及识别自然场景图像中的文本。尽管当前的STR最先进模型表现出高性能，但由于依赖由视觉编码器和序列解码器组成的混合架构，它们通常存在推理效率低下的问题。在这项工作中，我们提出了用于快速高效场景文本识别的视觉可置换提取器（VIPTR），它在STR领域实现了高性能与快速推理速度之间的显著平衡。具体而言，VIPTR采用具有金字塔结构的视觉语义提取器，其特点是包含多个自注意力层，同时摒弃了传统的序列解码器。这一设计选择产生了一个轻量级且高效的模型，能够处理不同尺寸的输入。在多个中英文场景文本识别的标准数据集上的大量实验结果验证了VIPTR的优越性。值得注意的是，VIPTR-T（微型）变体在达到与其他轻量级模型相当的高竞争性准确率的同时，实现了最先进的推理速度。同时，VIPTR-L（大型）变体在保持低参数数量和良好推理速度的情况下，获得了更高的识别准确率。我们提出的方法为解决STR挑战提供了一种有吸引力的方案，它将高准确率与高效性相结合，极大地惠及需要快速可靠文本识别的实际应用。代码已在 https://github.com/cxfyxl/VIPTR 公开。