透过频率之镜：基于自适应调制的跨域泛化视线估计
Through the Frequency Lens: Cross-Domain Generalisable Gaze Estimation with Adaptive Modulation
把图像分解到频域、用可学习调制图抑制样本级干扰频段并做频谱分布多样化，这套频域自适应调制思路可直接迁移到其他对域偏移敏感的人脸/人体回归任务（如头部姿态、面部关键点）的域泛化训练中。
原文依据 AISM adaptively suppresses sample-specific interfering frequency components through learnable modulation maps
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论基于深度学习的视线估计方法在未见过的目标域上往往出现显著的性能下降。通过系统的频域分析，我们揭示出人脸图像包含贡献各异的频率成分：部分成分有助于跨域泛化，另一些则引入域特定的干扰、阻碍泛化，且这两类成分随数据集而变化，构成域间差距的关键来源。基于这些观察，我们提出频率引导的自适应学习框架（FGAL），这是一个在不访问目标域数据的前提下增强域泛化的新框架。FGAL 由两个互补模块组成：自适应干扰抑制模块（AISM）与频谱多样化模块（SDM）。AISM 通过可学习的调制图自适应地抑制样本特定的干扰频率成分，SDM 则使频率分布模式多样化，以增强对跨域变化的鲁棒性。实验表明，FGAL 取得显著提升，在多种跨域设定下相较基线最高提升 28.2%，相较最优方法最高提升 19.5%，展现了该框架在更广泛域泛化任务中的潜力。
英文原文摘要 1277 字符
Deep learning-based gaze estimation methods often exhibit significant performance degradation on unseen target domains. Through systematic frequency-domain analysis, we reveal that face images contain frequency components with distinct contributions: some facilitate cross-domain generalization while others introduce domain-specific interference that impedes it, with both components varying across datasets and constituting a key source of domain gap. Based on these observations, we propose the Frequency-Guided Adaptive Learning framework (FGAL), a novel framework enhancing domain generalization without accessing target domain data. The FGAL consists of two complementary modules: the Adaptive Interference Suppression Module (AISM) and the Spectrum Diversification Module (SDM). AISM adaptively suppresses sample-specific interfering frequency components through learnable modulation maps, while SDM diversifies frequency distribution patterns to enhance robustness against cross-domain variations. Experiments demonstrate that FGAL achieves substantial improvements, outperforming baselines by up to 28.2% and state-of-the-art methods by up to 19.5% across multiple cross-domain settings, demonstrating our framework's potential for broader domain generalization tasks.