arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2109.03596cs.LGcs.HC
收藏

Learn2Agree:在没有客观真值的情况下使用多个注释器进行拟合

Learn2Agree: Fitting with Multiple Annotators without Objective Ground Truth

Tsinghua University(清华大学);Shenzhen Institute of Artificial Intelligence Robotics for Society(深圳人工智能与机器人研究院);South China Normal University(华南师范大学);University of Cambridge(剑桥大学);University College London(伦敦大学学院)

Chongyang Wang, Yuan Gao, Chenyou Fan, Junjie Hu, Tin Lun Lam, Nicholas D. Lane, Nadia Bianchi-Berthouze

摘要:

领域专家的注释对于某些医学应用是重要的,其中客观真值定义不明确,例如,一些慢性疾病的康复,以及一些肌肉骨骼异常的预先筛查,而无需进一步的医疗检查。然而,注释的不当使用可能会阻碍开发可靠的模型。一方面,强制使用从多个注释生成的单个真值对于建模来说信息量较少。另一方面,在没有适当正则化的情况下为模型提供所有注释是有噪声的,因为存在分歧。对于这些问题,我们提出了一个新的学习协议(Learn2Agree)框架,以解决从多个注释器学习的挑战,没有客观的真值。该框架有两个流,一个流适合多个注释器,另一个流学习注释器之间的协议信息。特别是,一致性学习流为分类器流产生正则化信息,调整其决策以更好地符合注释器之间的一致性。所提出的方法可以很容易地添加到现有的骨干,在两个医疗数据集上的实验显示出更好的一致性水平与注释。

英文摘要:

The annotation of domain experts is important for some medical applications where the objective ground truth is ambiguous to define, e.g., the rehabilitation for some chronic diseases, and the prescreening of some musculoskeletal abnormalities without further medical examinations. However, improper uses of the annotations may hinder developing reliable models. On one hand, forcing the use of a single ground truth generated from multiple annotations is less informative for the modeling. On the other hand, feeding the model with all the annotations without proper regularization is noisy given existing disagreements. For such issues, we propose a novel Learning to Agreement (Learn2Agree) framework to tackle the challenge of learning from multiple annotators without objective ground truth. The framework has two streams, with one stream fitting with the multiple annotators and the other stream learning agreement information between annotators. In particular, the agreement learning stream produces regularization information to the classifier stream, tuning its decision to be better in line with the agreement between annotators. The proposed method can be easily added to existing backbones, with experiments on two medical datasets showed better agreement levels with annotators.

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。

↑