论文标题
重新考虑学习范式以识别面部表情
Rethinking the Learning Paradigm for Facial Expression Recognition
论文作者
论文摘要
由于主观的众包注释和面部表情的固有类间相似性，现实世界的面部表达识别（FER）数据集通常表现出模棱两可的注释。为了简化学习范式，大多数以前的方法将模棱两可的注释结果转换为精确的一hot注释，并以端到端的监督方式训练FER模型。在本文中，我们重新考虑了现有的培训范式，并建议最好使用弱监督的策略来培训用原始含糊的注释训练FER模型。
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.
