基于最优教师池的动态标签噪声抑制用于面部表情识别
Dynamic Label Noise Suppression with Optimal Teacher Pool for Facial Expression Recognition
针对表情识别中标签歧义导致的噪声标签问题，提出动态维护多个最优教师模型并融合其预测的教师池机制，配合基于预测-标签相似度的自适应标签平滑与基于质心置信度的 logits 加权，可直接迁移到其他人脸/人体属性识别任务的噪声标签训练中。
原文依据 we construct an optimal teacher pool architecture that dynamically maintains multiple best teacher models while fusing their predictions
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论由于面部表情本身固有的歧义性以及数据集标注中的主观性，带噪声标签的学习仍然是面部表情识别（FER）中的关键挑战。教师-学生网络的监督机制为带噪声标签的 FER 提供了一种有前景的途径。然而，该方法在训练过程中容易出现噪声累积以及教师与学生参数之间的逐渐耦合。我们提出了一种面向面部表情识别的最优教师池驱动动态标签噪声抑制框架（OTP-NS）。具体而言，我们构建了一种最优教师池架构，动态维护多个最优教师模型并融合它们的预测，从而通过更新机制缓解噪声累积以及教师-学生参数的耦合。此外，我们设计了两个样本级的噪声抑制部分：（1）相似度感知标签平滑（SALS），它不同于传统标签平滑中静态的平滑强度，而是根据预测与标签的相似度自动为教师模型调节平滑强度，实现细粒度的噪声抑制。（2）置信度加权 logits（CWL），基于样本到质心的置信度度量自适应地调整学生模型的分类损失，缓解噪声样本对模型训练的不利影响。在多个基准数据集上的大量实验表明，我们的方法在不同噪声水平下均优于最优方法，验证了所提框架从噪声数据中学习鲁棒表征的有效性。
英文原文摘要 1617 字符
Due to the inherent ambiguity of facial expressions and subjectivity in dataset labeling, learning with noisy labels remains a critical challenge in facial expression recognition (FER). The supervisory mechanism of teacher-student network offers a promising approach for noisy-labeled FER. However, this approach is prone to noise accumulation and gradual coupling between the teacher and student parameters during training. We propose an Optimal Teacher Pool-driven dynamic label Noise Suppression framework for facial expression recognition (OTP-NS). Specifically, we construct an optimal teacher pool architecture that dynamically maintains multiple best teacher models while fusing their predictions, thereby mitigating noise accumulation and coupling of teacher-student parameters via update mechanisms. Furthermore, we develop two sample-level noise suppression parts: (1) Similarity-Aware Label Smoothing (SALS), diverging from the static smoothing strength in traditional label smoothing, automatically modulates the smoothing strength for teacher model based on prediction-label similarity, achieving fine-grained noise suppression. (2) Confidence-Weighted Logits (CWL), adaptively adjusting the classification loss of student model based on sample-to-centroid confidence metrics, alleviates the detrimental effects of noisy samples on model training. Extensive experiments on multiple benchmark datasets demonstrate that our method outperforms state-of-the-art approaches across various noise levels, validating the effectiveness of our proposed framework in learning robust representations from noisy data.