• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>Humaine Association Conference on Affective Computing and Intelligent Interaction >Facing Imbalanced Data--Recommendations for the Use of Performance Metrics
【24h】

Facing Imbalanced Data--Recommendations for the Use of Performance Metrics

机译：面对不平衡数据 - 使用性能指标的建议

获取原文
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Recognizing facial action units (AUs) is important for situation analysis and automated video annotation. Previous work has emphasized face tracking and registration and the choice of features classifiers. Relatively neglected is the effect of imbalanced data for action unit detection. While the machine learning community has become aware of the problem of skewed data for training classifiers, little attention has been paid to how skew may bias performance metrics. To address this question, we conducted experiments using both simulated classifiers and three major databases that differ in size, type of FACS coding, and degree of skew. We evaluated influence of skew on both threshold metrics (Accuracy, F-score, Cohen's kappa, and Krippendorf's alpha) and rank metrics (area under the receiver operating characteristic (ROC) curve and precision-recall curve). With exception of area under the ROC curve, all were attenuated by skewed distributions, in many cases, dramatically so. While ROC was unaffected by skew, precision-recall curves suggest that ROC may mask poor performance. Our findings suggest that skew is a critical factor in evaluating performance metrics. To avoid or minimize skew-biased estimates of performance, we recommend reporting skew-normalized scores along with the obtained ones.
机译：识别面部动作单位（AUS）对于情况分析和自动视频注释非常重要。以前的工作强调了面部跟踪和注册以及功能分类器的选择。相对忽略的是行动单元检测的不平衡数据的影响。虽然机器学习社区已经意识到训练分类器的偏斜数据问题，但对于偏斜可能偏见性能指标，已经提出了很少的关注。为了解决这个问题，我们使用模拟分类器和三个主要数据库进行了实验，这些数据库的大小不同，FACS编码的类型和偏斜程度。我们评估了偏斜对阈值指标（准确性，F分，Cohen的Kappa和Krippendorf的alpha）和秩指标（接收器操作特征（Roc）曲线和精密召回曲线的区域）的影响。除了ROC曲线下的面积外，所有人都在许多情况下倾斜分布衰减，大幅下榻。虽然ROC不受歪斜的影响，但精密召回曲线表明ROC可能会掩盖性能不佳。我们的研究结果表明，歪斜是评估绩效指标的关键因素。为避免或最大限度地减少偏置偏差的性能估计，我们建议将偏斜标准化分数与所获得的分数报告。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号