English

Test-Time Personalization with Meta Prompt for Gaze Estimation

Computer Vision and Pattern Recognition 2024-03-14 v3

Abstract

Despite the recent remarkable achievement in gaze estimation, efficient and accurate personalization of gaze estimation without labels is a practical problem but rarely touched on in the literature. To achieve efficient personalization, we take inspiration from the recent advances in Natural Language Processing (NLP) by updating a negligible number of parameters, "prompts", at the test time. Specifically, the prompt is additionally attached without perturbing original network and can contain less than 1% of a ResNet-18's parameters. Our experiments show high efficiency of the prompt tuning approach. The proposed one can be 10 times faster in terms of adaptation speed than the methods compared. However, it is non-trivial to update the prompt for personalized gaze estimation without labels. At the test time, it is essential to ensure that the minimizing of particular unsupervised loss leads to the goals of minimizing gaze estimation error. To address this difficulty, we propose to meta-learn the prompt to ensure that its updates align with the goal. Our experiments show that the meta-learned prompt can be effectively adapted even with a simple symmetry loss. In addition, we experiment on four cross-dataset validations to show the remarkable advantages of the proposed method. Code is available at https://github.com/hmarkamcan/TPGaze.

Keywords

Cite

@article{arxiv.2401.01577,
  title  = {Test-Time Personalization with Meta Prompt for Gaze Estimation},
  author = {Huan Liu and Julia Qi and Zhenhao Li and Mohammad Hassanpour and Yang Wang and Konstantinos Plataniotis and Yuanhao Yu},
  journal= {arXiv preprint arXiv:2401.01577},
  year   = {2024}
}

Comments

Accepted by AAAI 2024

R2 v1 2026-06-28T14:07:34.156Z