Collaborative contrastive learning for cross-domain gaze estimation

Gaze estimation methods commonly rely on single-camera facial appearance analysis to estimate the direction of a person's gaze. Recently, there has been significant interest in exploring gaze estimation techniques across different domains. Despite the advances, distinguishing authentic gaze-relevant features primarily relies on detecting subtle changes in the eye region. Moreover, non-gaze-related features are intricately entangled with the gaze-relevant components in a nonlinear manner. In response to these challenges, our work addresses the cross-domain gaze estimation problem through a feature decontaminating approach. Specifically, we propose a Cross Gaze Generalization (CGaG) method that explicitly encodes gaze- and domain-dedicated feature and leverages cross-identity features swapping to generate novel images where changes are exclusively confined to either the gaze or domain attributes. To consolidate feature purification and domain generalization, we utilize the equivariance between images and gaze labels to facilitate collaborative contrastive learning (CCL), which faithfully ensures that the generated novel images align with the expected outputs. Extensive experiments are conducted on various cross-domain tasks, demonstrating the effectiveness of CGaG. Meanwhile, CGaG achieves superior or comparable gaze estimation accuracy on both domain generalization and domain adaptation experiments. CGaG also shows promising cross-identity gaze or domain transfer visualizations. © 2024