Despite remarkable advancements, mainstream gaze estimation techniques, particularly appearance-based methods, often suffer from performance degradation in uncontrolled environments due to variations in illumination and individual facial attributes. Existing domain adaptation strategies, limited by their need for target domain samples, may fall short in real-world applications. This letter introduces Branch-out Auxiliary Regularization (BAR), an innovative method designed to boost gaze estimation's generalization capabilities without requiring direct access to target domain data. Specifically, BAR integrates two auxiliary consistency regularization branches: one that uses augmented samples to counteract environmental variations, and another that aligns gaze directions with positive source domain samples to encourage the learning of consistent gaze features. These auxiliary pathways strengthen the core network and are integrated in a smooth, plug-and-play manner, facilitating easy adaptation to various other models. Comprehensive experimental evaluations on four cross-dataset tasks demonstrate the superiority of our approach.

翻译：尽管取得了显著进展，主流视线估计技术（尤其是基于外观的方法）常因光照变化及个体面部属性差异，在非受控环境中出现性能下降。现有领域适应策略受限于对目标域样本的需求，在实际应用中可能效果不佳。本文提出分支辅助正则化（Branch-out Auxiliary Regularization, BAR），这是一种无需直接访问目标域数据即可提升视线估计泛化能力的创新方法。具体而言，BAR集成了两个辅助一致性正则化分支：其一利用增强样本应对环境变化，其二通过将视线方向与正向源域样本对齐，促进学习一致的视线特征。这些辅助路径增强了核心网络，并以平滑的即插即用方式集成，便于轻松适配其他模型。在四个跨数据集任务上的综合实验评估证明了本方法的优越性。