面向场景文本识别的关系对比学习
Relational Contrastive Learning for Scene Text Recognition
AI总结：
针对场景文本识别中因数据集有限和词汇依赖导致的文本关系受限及过拟合问题，提出统一框架RCLSTR，通过重排、层次和交互丰富文本关系，并基于因果性抑制上下文先验偏差以增强表示鲁棒性，实验证明其优于现有自监督方法。
摘要：
上下文感知方法通过结合来自单词的语义先验，在有监督场景文本识别中取得了巨大成功。我们认为，由于文本和背景的异构性，这种先验上下文信息可以被解释为文本基元的关系，这可以为表示学习提供有效的自监督标签。然而，由于词汇依赖性，文本关系受限于数据集的有限规模，这会导致过拟合问题并损害表示的鲁棒性。为此，我们提出通过重排、层次和交互来丰富文本关系，并设计了一个统一框架RCLSTR：面向场景文本识别的关系对比学习。基于因果性，我们在理论上解释了这三个模块能够抑制由上下文先验引起的偏差，从而保证表示的鲁棒性。关于表示质量的实验表明，我们的方法优于最先进的自监督STR方法。代码可在https://github.com/ThunderVVV/RCLSTR获取。
英文摘要：
Context-aware methods achieved great success in supervised scene text recognition via incorporating semantic priors from words. We argue that such prior contextual information can be interpreted as the relations of textual primitives due to the heterogeneous text and background, which can provide effective self-supervised labels for representation learning. However, textual relations are restricted to the finite size of dataset due to lexical dependencies, which causes the problem of over-fitting and compromises representation robustness. To this end, we propose to enrich the textual relations via rearrangement, hierarchy and interaction, and design a unified framework called RCLSTR: Relational Contrastive Learning for Scene Text Recognition. Based on causality, we theoretically explain that three modules suppress the bias caused by the contextual prior and thus guarantee representation robustness. Experiments on representation quality show that our method outperforms state-of-the-art self-supervised STR methods. Code is available at https://github.com/ThunderVVV/RCLSTR.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
