AI 中文总结
针对细粒度FER中局部证据稀释问题，提出SRE-FER框架，通过RERA模块和AU指导优化，在三个基准测试中取得具竞争力的FER性能。
AI 中文摘要
细粒度面部表情识别（FER）依赖于捕捉区分相邻情感的细微肌肉线索，但这一过程存在两难：基于检测器的方法依赖脆弱的关键点流程，而我们发现，在传统全局读出下直接迁移DINOv3等基础模型会导致局部证据稀释——早期全局聚合会冲刷稀疏的肌肉信号，使恐惧/惊讶、悲伤/中性等类别间持续混淆。为恢复该证据，我们提出SRE-FER，一种读出级区域残差证据学习框架，其核心模块RERA添加零初始化残差logits，在保留主干全局预测的同时细化类别边界；训练时的动作单元（AU）指导利用基于面部动作编码系统（FACS）的解剖学先验，将区域特征导向表情相关区域，推理时无需外部面部流程；可选的Full设置进一步路由样本特定的非冗余token。在三个基准测试中，SRE-FER在RAF-DB上达到92.76%，FERPlus上达到91.32%，AffectNet-7上达到67.78%，展现出与现有FER方法相比极具竞争力的性能。
英文摘要
Fine-grained facial expression recognition (FER) hinges on capturing subtle muscular cues that distinguish adjacent emotions. Yet capturing these cues presents a dilemma. Detector-based methods depend on fragile landmark pipelines, whereas we find that directly transferring foundation models such as DINOv3 under conventional global readouts can cause local evidence dilution: early global aggregation washes out sparse muscular signals and leaves persistent confusion between categories such as fear/surprise and sad/neutral. To recover this evidence, we propose SRE-FER, a readout-level regional residual evidence learning framework. Its core module, RERA, adds zero-initialized residual logits that refine class boundaries while preserving the backbone's global prediction. Training-time action unit (AU) guidance steers regional features toward expression-relevant areas using Facial Action Coding System (FACS)-based anatomical priors, without requiring an external facial pipeline at inference. An optional Full setting further routes sample-specific non-redundant tokens. On three benchmarks, SRE-FER attains 92.76% on RAF-DB, 91.32% on FERPlus, and 67.78% on AffectNet-7, demonstrating highly competitive performance compared to existing FER methods.
Comments10 pages, 5 figures.Accepted at the 9th International Conference on Artificial Intelligence and Pattern Recognition (AIPR 2026)
