Domain Adaptation Gaze Estimation by Embedding with Prediction Consistency
This work addresses the domain adaptation challenge in gaze estimation for applications like human-computer interaction, though it appears incremental as it builds on existing methods to reduce inter-personal diversity.
The paper tackles the problem of inter-personal differences limiting subject-independent gaze estimation accuracy by proposing an unsupervised domain adaptation method that uses embedding with prediction consistency to align gaze directions across domains. It achieves state-of-the-art results on the MPIIGaze and EYEDIAP datasets.
Gaze is the essential manifestation of human attention. In recent years, a series of work has achieved high accuracy in gaze estimation. However, the inter-personal difference limits the reduction of the subject-independent gaze estimation error. This paper proposes an unsupervised method for domain adaptation gaze estimation to eliminate the impact of inter-personal diversity. In domain adaption, we design an embedding representation with prediction consistency to ensure that the linear relationship between gaze directions in different domains remains consistent on gaze space and embedding space. Specifically, we employ source gaze to form a locally linear representation in the gaze space for each target domain prediction. Then the same linear combinations are applied in the embedding space to generate hypothesis embedding for the target domain sample, remaining prediction consistency. The deviation between the target and source domain is reduced by approximating the predicted and hypothesis embedding for the target domain sample. Guided by the proposed strategy, we design Domain Adaptation Gaze Estimation Network(DAGEN), which learns embedding with prediction consistency and achieves state-of-the-art results on both the MPIIGaze and the EYEDIAP datasets.