arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2012.12643cs.CVcs.LG
收藏

场景-文本识别模型的标定

On Calibration of Scene-Text Recognition Models

Technion(以色列理工学院);Amazon Web Services(亚马逊云科技)

Ron Slossberg, Oron Anschel, Amir Markovitz, Ron Litman, Aviad Aberdam, Shahar Tsiper, Shai Mazor, Jon Wu, R. Manmatha

摘要:

在这项工作中,我们研究了场景文本识别(STR)的单词级置信度校准问题。虽然置信度校准的主题在过去几十年中一直是一个活跃的研究领域,但结构化和序列预测校准的情况却很少被探索。我们分析了几个最近的STR方法,并表明他们一贯过度自信。然后,我们专注于STR模型在单词而不是字符水平上的校准。特别是,我们证明,注意基于解码器,校准的单个字符的预测增加字级校准误差相比,未校准的模型。此外,我们将现有的校准方法以及新的基于序列的扩展应用于众多STR模型,证明校准误差降低了近7倍。最后,我们通过将我们提出的序列校准方法作为预处理步骤应用于波束搜索,显示了一致的精度提高结果。

英文摘要:

In this work, we study the problem of word-level confidence calibration for scene-text recognition (STR). Although the topic of confidence calibration has been an active research area for the last several decades, the case of structured and sequence prediction calibration has been scarcely explored. We analyze several recent STR methods and show that they are consistently overconfident. We then focus on the calibration of STR models on the word rather than the character level. In particular, we demonstrate that for attention based decoders, calibration of individual character predictions increases word-level calibration error compared to an uncalibrated model. In addition, we apply existing calibration methodologies as well as new sequence-based extensions to numerous STR models, demonstrating reduced calibration error by up to a factor of nearly 7. Finally, we show consistently improved accuracy results by applying our proposed sequence calibration method as a preprocessing step to beam-search.

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。

↑