Test-Time Personalization with Meta Prompt for Gaze Estimation
Proceedings of the AAAI Conference on Artificial Intelligence · 24.03.2024 · 38 (4) · 3621-3629
DOI: 10.1609/aaai.v38i4.28151 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 24.03.2024. Verfasst von Huan Liu und 6 weiteren Autor:innen. Die Arbeit wurde bisher 10-mal zitiert (Crossref).
Abstract (Originalsprache)
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.
Zitieren
APA
Liu, H., Qi, J., Li, Z., Hassanpour, M., Wang, Y., Plataniotis, K. N., & Yu, Y. (2024). Test-Time Personalization with Meta Prompt for Gaze Estimation. Proceedings of the AAAI Conference on Artificial Intelligence, 38(4), 3621-3629. https://doi.org/10.1609/aaai.v38i4.28151
Vancouver
Liu H, Qi J, Li Z, Hassanpour M, Wang Y, Plataniotis KN, et al. Test-Time Personalization with Meta Prompt for Gaze Estimation. Proceedings of the AAAI Conference on Artificial Intelligence. 2024;38(4):3621-3629. doi:10.1609/aaai.v38i4.28151
BibTeX
@article{Liu2024,
author = {Liu, Huan and Qi, Julia and Li, Zhenhao and Hassanpour, Mohammad and Wang, Yang and Plataniotis, Konstantinos N. and Yu, Yuanhao},
title = {Test-Time Personalization with Meta Prompt for Gaze Estimation},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2024},
volume = {38},
number = {4},
pages = {3621--3629},
doi = {10.1609/aaai.v38i4.28151}
}
EUVIMED