FER-C：面向面部表情识别的分布外软校准基准测试
FER-C: Benchmarking Out-of-Distribution Soft Calibration for Facial Expression Recognition
AI总结：
该研究提出FER-C软基准，针对面部表情识别模型校准偏差及分布外偏移加剧的表情模糊问题，采用能近似不同OOD偏移下平均信息损失的软标签，验证了校准对五种先进FER算法的提升作用。
摘要：
我们提出了一个用于校准面部表情识别（FER）的软基准。现有研究多聚焦于识别情感状态，但我们发现FER模型存在校准偏差，在分布外（OOD）偏移进一步加剧面部表情模糊性时尤为明显。多数OOD基准采用硬标签，而我们认为评估FER模型的真实标签应为软标签，以更好地反映面部行为背后的模糊性。我们的框架提出了能近似不同类型OOD偏移下平均信息损失的软标签。最后，我们在该基准上测试了五种先进FER算法，验证了校准的优势。
英文摘要：
We present a soft benchmark for calibrating facial expression recognition (FER). While prior works have focused on identifying affective states, we find that FER models are uncalibrated. This is particularly true when out-of-distribution (OOD) shifts further exacerbate the ambiguity of facial expressions. While most OOD benchmarks provide hard labels, we argue that the ground-truth labels for evaluating FER models should be soft in order to better reflect the ambiguity behind facial behaviours. Our framework proposes soft labels that closely approximates the average information loss based on different types of OOD shifts. Finally, we show the benefits of calibration on five state-of-the-art FER algorithms tested on our benchmark.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
