无需源数据的脑电情绪识别域适应方法，提升跨人群应用性能。
Towards Practical Emotion Recognition: An Unsupervised Source-Free Approach for EEG Domain Adaptation
- 无源数据条件下，通过伪标签与一致性学习实现跨域适配。
- 在SEED和DREAMER上达到58.87%与67.08%准确率，显著优于现有方法。
- 适用于隐私敏感场景，适合真实世界情绪识别系统部署。
情绪识别对心理健康、医疗及脑机接口等技术至关重要。基于脑电（EEG）的模型在跨域设置中表现不佳，主要受限于标注数据成本高及个体间信号差异大。传统无监督域适应需访问源数据，常因隐私与计算限制无法实现。源无关无监督域适应（SF-UDA）可规避此问题，但尚未用于情绪识别。本文提出一种基于多阶段框架的SF-UDA方法，无需源数据即可适配目标域。通过双损失自适应正则化（DLAR）最小化置信样本的预测差异，并对齐预测与期望伪标签；局部一致性学习（LCL）通过强化可靠邻域内预测的一致性，缓解噪声伪标签影响。在DEAP、SEED和DREAMER数据集上的实验表明，该方法显著优于当前最优方法：当在DEAP上训练时，在SEED和DREAMER上分别取得65.84%和58.87%准确率；在SEED上训练时，在DEAP和DREAMER上分别达到58.99%和67.08%。能有效识别正负情绪，具备实际应用潜力。代码已开源：https://github.com/RyersonMultimediaLab/EmotionRecognitionSF-UDA
原文摘要 · Abstract (English)
Emotion recognition is crucial for advancing mental health, healthcare, and technologies such as brain-computer interfaces. EEG-based models, however, struggle in cross-domain settings due to the high cost of labeled data and signal variability across individuals and recording conditions. Unsupervised domain adaptation typically requires access to source data, which is often infeasible because of privacy and computational constraints. Source-free unsupervised domain adaptation (SF-UDA) removes this requirement, but it has not yet been applied to emotion recognition. We propose an SF-UDA approach for cross-domain EEG emotion classification, built on a multi-stage framework that adapts to the target domain without source data. Dual-Loss Adaptive Regularization (DLAR) minimizes prediction discrepancies on confident samples and aligns predictions with expected pseudo-labels. Localized Consistency Learning (LCL) enforces local consistency by promoting similar predictions among reliable neighbors. Together, these components address domain shift and reduce the impact of noisy pseudo-labels, a key challenge in SF-UDA. Experiments on DEAP, SEED, and DREAMER show that our method significantly outperforms state-of-the-art approaches, reaching 65.84% and 58.87% accuracy on SEED and DREAMER when trained on DEAP, and 58.99% and 67.08% on DEAP and DREAMER when trained on SEED. It detects both positive and negative emotions well, making it suitable for practical emotion recognition applications. Code available at: https://github.com/RyersonMultimediaLab/EmotionRecognitionSF-UDA
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。