用图注意力与对抗对齐提升跨域表情识别准确率
Graph-Attention Network with Adversarial Domain Alignment for Robust Cross-Domain Facial Expression Recognition
- 构建批次级图结构，用注意力聚合样本间跨域线索
- 在5个测试集上均值达74.39%，最高提升36个百分点
- 适合处理训练与部署数据差异大的表情识别场景
跨域面部表情识别（CD-FER）因训练与部署数据间严重分布偏移而困难。本文提出图注意力网络与对抗域对齐框架（GAT-ADA），将ResNet-50作为主干，结合批次级图注意力网络（GAT）建模样本间关系。每个小批量被构造成稀疏环图，通过注意力机制聚合对适应有帮助的跨样本信息。为实现分布对齐，GAT-ADA融合梯度反转层（GRL）的对抗学习与CORAL和MMD的统计对齐。在标准无监督域自适应协议下评估：在标注源数据RAF-DB上训练，适配多个无标签目标数据集（CK+、JAFFE、SFEW 2.0、FER2013、ExpW）。GAT-ADA达到74.39%的平均跨域准确率。在RAF-DB到FER2013的迁移任务中，准确率达98.0%，相比复现的最佳基线提升约36个百分点。
原文摘要 · Abstract (English)
Cross-domain facial expression recognition (CD-FER) remains difficult due to severe domain shift between training and deployment data. We propose Graph-Attention Network with Adversarial Domain Alignment (GAT-ADA), a hybrid framework that couples a ResNet-50 as backbone with a batch-level Graph Attention Network (GAT) to model inter-sample relations under shift. Each mini-batch is cast as a sparse ring graph so that attention aggregates cross-sample cues that are informative for adaptation. To align distributions, GAT-ADA combines adversarial learning via a Gradient Reversal Layer (GRL) with statistical alignment using CORAL and MMD. GAT-ADA is evaluated under a standard unsupervised domain adaptation protocol: training on one labeled source (RAF-DB) and adapting to multiple unlabeled targets (CK+, JAFFE, SFEW 2.0, FER2013, and ExpW). GAT-ADA attains 74.39% mean cross-domain accuracy. On RAF-DB to FER2013, it reaches 98.0% accuracy, corresponding to approximately a 36-point improvement over the best baseline we re-implemented with the same backbone and preprocessing.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。