Jitter Does Matter: Adapting Gaze Estimation to New Domains
This work addresses cross-domain gaze estimation for computer vision applications, but it is incremental as it builds on existing domain adaptation methods by focusing on a specific phenomenon.
The paper tackles the problem of gaze estimation performance degrading when models are applied to new domains due to variations like person, illumination, and background, and it shows that reducing gaze jitter through high-frequency component analysis improves performance, with experimental results demonstrating significant reductions in jitter and gains in target domains.
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.