Generalizing Gaze Estimation with Outlier-guided Collaborative Adaptation

TL;DR

This paper introduces PnP-GA, a plug-and-play ensemble framework that improves gaze estimation across different domains without requiring target domain labels, significantly outperforming existing methods.

Contribution

The paper proposes a novel outlier-guided collaborative adaptation framework for gaze estimation that does not need ground-truth labels in new domains, enabling direct plug-and-play application of existing models.

Findings

Achieves up to 36.9% performance improvement over baseline.

Outperforms state-of-the-art domain adaptation methods.

Effective across multiple gaze domain adaptation tasks.

Abstract

Deep neural networks have significantly improved appearance-based gaze estimation accuracy. However, it still suffers from unsatisfactory performance when generalizing the trained model to new domains, e.g., unseen environments or persons. In this paper, we propose a plug-and-play gaze adaptation framework (PnP-GA), which is an ensemble of networks that learn collaboratively with the guidance of outliers. Since our proposed framework does not require ground-truth labels in the target domain, the existing gaze estimation networks can be directly plugged into PnP-GA and generalize the algorithms to new domains. We test PnP-GA on four gaze domain adaptation tasks, ETH-to-MPII, ETH-to-EyeDiap, Gaze360-to-MPII, and Gaze360-to-EyeDiap. The experimental results demonstrate that the PnP-GA framework achieves considerable performance improvements of 36.9%, 31.6%, 19.4%, and 11.8% over the baseline system. The proposed framework also outperforms the state-of-the-art domain adaptation approaches on gaze domain adaptation tasks.