预测人类分歧以实现校准的动态面部表情识别
Predicting Human Disagreement for Calibrated Dynamic Facial Expression Recognition
浏览论文内容
中文总结 AI 辅助
提出分歧感知的DFER框架，用Dirichlet-Multinomial似然直接训练标注计数，结合模糊性头与拒绝规则，在DFEW上降ECE 30%、AURC 15%，并迁移至FERV39k。
中文摘要 AI 辅助
动态面部表情识别（DFER）基准如DFEW为每个视频片段提供多个标注者的投票，但大多数模型将其压缩为多数标签，无法在推理时表示人类分歧。我们提出了一种分歧感知的DFER框架，该框架直接基于原始标注者计数向量进行训练，使用Dirichlet-Multinomial似然。与仅均值的软标签目标不同，所提出的似然为Dirichlet浓度提供了尺度敏感的监督，同时保留了预测均值。一个独立的模糊性头预测未见片段的标注熵，一个单调的Chow式拒绝规则结合预测模糊性、空虚性、时间不稳定性和输入质量进行选择性预测。在DFEW上，该方法在保持识别精度的同时，将ECE降低了30%，AURC降低了15%，预测模糊性与测试片段的标注熵达到0.52的Spearman相关性。校准和选择性预测的收益可迁移至FERV39k，并在身份和电影不相交的DFEW划分下保持。
英文摘要
Dynamic facial expression recognition (DFER) benchmarks such as DFEW provide multiple annotator votes per clip, yet most models collapse them to a majority label and cannot represent human disagreement at inference time. We propose a disagreement-aware DFER framework that trains directly on the raw annotator count vector using a Dirichlet-Multinomial likelihood. Unlike mean-only soft-label objectives, the proposed likelihood provides scale-sensitive supervision for the Dirichlet concentration while preserving the predictive mean. A separate ambiguity head predicts annotation entropy for unseen clips, and a monotone Chow-style reject rule combines predicted ambiguity, vacuity, temporal instability, and input quality for selective prediction. On DFEW, the method preserves recognition accuracy while reducing ECE by 30% and AURC by 15%, and predicted ambiguity reaches a Spearman correlation of 0.52 with the annotation entropy of test clips. The calibration and selective-prediction gains transfer to FERV39k and remain under identity- and movie-disjoint DFEW splits.
发表机构
- Durham University（杜伦大学）
机构由 AI 辅助整理，请以论文原文为准。
