Abstract
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 this https URL.
Abstract (translated)
场景文本识别(STR)是一个具有挑战性的任务,涉及在自然场景图像中识别文本。尽管当前最先进的STR模型具有很高的性能,但它们通常由于依赖视觉编码器和解码器的混合架构而具有低推理效率。在这项工作中,我们提出了一种名为视觉可持久提取器(VIPTR)的快速高效的场景文本识别(STR)方法,在STR领域实现了高性能和快速推理速度之间的令人印象深刻的平衡。具体来说,VIPTR利用具有金字塔结构的视觉语义提取器,其中包含多个自注意力层,而跳过了传统的序列解码器。这种设计选择导致了一个轻量级且高效的模型,能够处理各种输入大小的数据。对中文和英文场景文本识别的各种标准数据集的实验结果证实了VIPTR具有卓越的优越性。值得注意的是,VIPTR-T(小型)变体在与其他轻量级模型的竞争中具有高度的准确性,并实现了与SOTA推理速度相当的性能。同时,VIPTR-L(大型)变体具有更高的识别准确性,而参数数量较少,推理速度有利。我们提出的方法为STR挑战提供了一个引人注目的解决方案,将高准确性与效率相结合,大大有益于需要快速可靠文本识别的实时应用。代码公开在https://这个URL上。
URL
https://arxiv.org/abs/2401.10110