Due to the subjective crowdsourcing annotations and the inherent inter-class similarity of facial expressions, the real-world Facial Expression Recognition (FER) datasets usually exhibit ambiguous annotation. To simplify the learning paradigm, most previous methods convert ambiguous annotation results into precise one-hot annotations and train FER models in an end-to-end supervised manner. In this paper, we rethink the existing training paradigm and propose that it is better to use weakly supervised strategies to train FER models with original ambiguous annotation.

翻译：由于主观的众包说明,以及面部表情内在的阶级间相似性,真实世界的面部表现识别数据集通常表现出模糊的注解。为了简化学习范式,大多数以往的方法将模糊的注解结果转换为精确的一热注解,并以端对端监督的方式培训FER模式。在本文件中,我们重新思考现有的培训模式,并提议最好使用受监管薄弱的战略,用原始的模糊注解来培训FER模式。