arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2108.08504cs.CVcs.AIcs.LGcs.MM
收藏

人脸表情识别中标注偏差的理解与消除

Understanding and Mitigating Annotation Bias in Facial Expression Recognition

University of California, Los Angeles(加州大学洛杉矶分校)

Yunliang Chen, Jungseock Joo

摘要:

计算机视觉模型的性能取决于其训练数据的大小和质量。最近的研究揭示了常见图像数据集中以前未知的成分偏差,这些偏差导致模型输出偏斜,并提出了减轻这些偏差的方法。然而,大多数现有的作品假设人类生成的注释可以被认为是黄金标准和公正的。在本文中,我们揭示了这种假设可能是有问题的,并且应该特别注意防止模型学习这种注释偏差。我们专注于面部表情识别,并比较实验室控制和野生数据集之间的标签偏差。我们证明了许多表情数据集在性别之间存在显著的注释偏差,特别是在快乐和愤怒的表情方面,并且传统方法无法完全减轻训练模型中的这种偏差。为了消除表情注释偏差,我们提出了一个AU校准的面部表情识别(AUC-FER)框架,利用面部动作单元(AU),并将三重损失的目标函数。实验结果表明,该方法是更有效地消除表达式注释偏见比现有的技术。

英文摘要:

The performance of a computer vision model depends on the size and quality of its training data. Recent studies have unveiled previously-unknown composition biases in common image datasets which then lead to skewed model outputs, and have proposed methods to mitigate these biases. However, most existing works assume that human-generated annotations can be considered gold-standard and unbiased. In this paper, we reveal that this assumption can be problematic, and that special care should be taken to prevent models from learning such annotation biases. We focus on facial expression recognition and compare the label biases between lab-controlled and in-the-wild datasets. We demonstrate that many expression datasets contain significant annotation biases between genders, especially when it comes to the happy and angry expressions, and that traditional methods cannot fully mitigate such biases in trained models. To remove expression annotation bias, we propose an AU-Calibrated Facial Expression Recognition (AUC-FER) framework that utilizes facial action units (AUs) and incorporates the triplet loss into the objective function. Experimental results suggest that the proposed method is more effective in removing expression annotation bias than existing techniques.

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。

↑