论文标题
抖动确实很重要：将目光估算到新领域
Jitter Does Matter: Adapting Gaze Estimation to New Domains
论文作者
论文摘要
深度神经网络在基于外观的凝视估计任务上表现出了出色的表现。但是，由于个人，照明和背景的变化，在将模型应用于新领域时，性能会大大降低。在本文中，我们在跨域凝视估计中发现了一种有趣的凝视抖动现象，即，在目标域中可能会严重偏离两个相似图像的凝视预测。这与跨域凝视估计任务密切相关，但令人惊讶的是，以前尚未注意到。因此，我们创新建议利用凝视抖动来分析和优化目光域的适应任务。我们发现高频组件（HFC）是导致抖动的重要因素。基于这一发现，我们使用对抗性攻击添加了高频组件在输入图像中，并采用对比度学习来鼓励模型获得原始数据和扰动数据之间的相似表示，从而降低了HFC的影响。我们在四个跨域凝视估计任务上评估了所提出的方法，实验结果表明，它大大减少了凝视抖动并改善目标域中的凝视估计性能。
Deep neural networks have demonstrated superior performance on appearance-based gaze estimation tasks. However, due to variations in person, illuminations, and background, performance degrades dramatically when applying the model to a new domain. In this paper, we discover an interesting gaze jitter phenomenon in cross-domain gaze estimation, i.e., the gaze predictions of two similar images can be severely deviated in target domain. This is closely related to cross-domain gaze estimation tasks, but surprisingly, it has not been noticed yet previously. Therefore, we innovatively propose to utilize the gaze jitter to analyze and optimize the gaze domain adaptation task. We find that the high-frequency component (HFC) is an important factor that leads to jitter. Based on this discovery, we add high-frequency components to input images using the adversarial attack and employ contrastive learning to encourage the model to obtain similar representations between original and perturbed data, which reduces the impacts of HFC. We evaluate the proposed method on four cross-domain gaze estimation tasks, and experimental results demonstrate that it significantly reduces the gaze jitter and improves the gaze estimation performance in target domains.
