When recognizing emotions, subtle nuances in displays of emotion generate ambiguity or uncertainty in emotion perception. Emotion uncertainty has been previously interpreted as inter-rater disagreement among multiple annotators. In this paper, we consider a more common and challenging scenario: modeling emotion uncertainty when only single emotion labels are available. From a Bayesian perspective, we propose to use deep ensembles to capture uncertainty for multiple emotion descriptors, i.e., action units, discrete expression labels and continuous descriptors. We further apply iterative self-distillation. Iterative distillation over multiple generations significantly improves performance in both emotion recognition and uncertainty estimation. Our method generates single student models that provide accurate estimates of uncertainty for in-domain samples and a student ensemble that can detect out-of-domain samples. Our experiments on emotion recognition and uncertainty estimation using the Aff-wild2 dataset demonstrate that our algorithm gives more reliable uncertainty estimates than both Temperature Scaling and Monte Carol Dropout.
翻译:当识别情感时,情感表现中的细微细细细细在情感感知中产生模糊或不确定。情感不确定性以前被解释为多个说明者之间的跨时代分歧。在本文中,我们考虑一种更常见和更具挑战性的设想:在只有单一情感标签的情况下,建模情感不确定性。从巴伊西亚的角度来看,我们提议使用深层的组合来捕捉多种情感描述器的不确定性,即动作单位、离散表达标签和连续描述器。我们进一步应用了迭代自我蒸馏。多代人的循环蒸馏极大地改善了情感识别和不确定性估计的性能。我们的方法生成了单一的学生模型,为体内样本和学生群提供准确的不确定性估计,从而能够探测外部样本。我们利用Aff-wild2数据集进行的情感识别和不确定性估算实验表明,我们的算法提供了比温度缩放和蒙特·卡罗尔流出更可靠的不确定性估算值。