迈向摆脱语言偏差与OCR错误：以语义为中心的文本视觉问答
Towards Escaping from Language Bias and OCR Error: Semantics-Centered Text Visual Question Answering
AI总结：
针对TextVQA中语言偏差和OCR错误问题，提出以语义为中心的SC-Net网络，通过实例级对比语义预测和语义中心Transformer模块，显著提升性能。
摘要：
场景图像中的文本传达了用于场景理解和推理的关键信息。在基于文本的视觉问答（TextVQA）过程中，模型的阅读和推理能力至关重要。然而，当前的TextVQA模型并未以文本为中心，且存在若干局限性。由于在答案预测过程中缺乏语义引导，模型容易受到语言偏差和光学字符识别（OCR）错误的主导。在本文中，我们提出了一种新颖的以语义为中心的网络（SC-Net），该网络包含一个实例级对比语义预测模块（ICSP）和一个以语义为中心的Transformer模块（SCT）。配备这两个模块后，以语义为中心的模型能够抵抗语言偏差和来自OCR的累积错误。在TextVQA和ST-VQA数据集上的大量实验证明了我们模型的有效性。SC-Net以显著的幅度超越了以往的工作，并且对于TextVQA任务更为合理。
英文摘要：
Texts in scene images convey critical information for scene understanding and reasoning. The abilities of reading and reasoning matter for the model in the text-based visual question answering (TextVQA) process. However, current TextVQA models do not center on the text and suffer from several limitations. The model is easily dominated by language biases and optical character recognition (OCR) errors due to the absence of semantic guidance in the answer prediction process. In this paper, we propose a novel Semantics-Centered Network (SC-Net) that consists of an instance-level contrastive semantic prediction module (ICSP) and a semantics-centered transformer module (SCT). Equipped with the two modules, the semantics-centered model can resist the language biases and the accumulated errors from OCR. Extensive experiments on TextVQA and ST-VQA datasets show the effectiveness of our model. SC-Net surpasses previous works with a noticeable margin and is more reasonable for the TextVQA task.
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。
