Harnessing Label Uncertainty to Improve Modeling: An Application to Student Engagement Recognition

Automatic facial expression recognition systems are usually trained from target labels that model each example as belonging unambiguously to a single class (e.g., "non-engaged", "very engaged", etc.). However, in some settings, ground-truth labels can be more aptly modeled as probability distributions (e.g., [0.1, 0.1, 0.5, 0.3] over 4 engagement categories) that capture the uncertainty that can arise during the annotation process. In this paper, we explore how harnessing the full probability distribution of each label ("soft labels"), rather than just a scalar summary statistic ("hard labels", e.g., majority class or mean), can yield better recognition accuracy when training automated detectors. Our results on a face image dataset (10698 faces over 20 subjects) labeled for perceived student engagement suggest that training on soft labels can deliver engagement detectors that fit the data stat. sig. more accurately (lower cross-entropy for classification, higher Pearson correlation for regression) than when training on hard labels. Moreover, we explore possible reasons for this effect and provide evidence that it is due to implicit regularization that the soft labels enact on the trained engagement detector. This effect is similar to, but empirically seems stronger than, the "label smoothing" approach proposed by Szegedy, et al. [1].