Gaze Label Alignment: Alleviating Domain Shift for Gaze Estimation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zeng, Guanzhong, Wang, Jingjing, Xu, Zefu, Yin, Pengwei, Ren, Wenqi, Xie, Di, Zhu, Jiang
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917875473711104
author Zeng, Guanzhong
Wang, Jingjing
Xu, Zefu
Yin, Pengwei
Ren, Wenqi
Xie, Di
Zhu, Jiang
author_facet Zeng, Guanzhong
Wang, Jingjing
Xu, Zefu
Yin, Pengwei
Ren, Wenqi
Xie, Di
Zhu, Jiang
contents Gaze estimation methods encounter significant performance deterioration when being evaluated across different domains, because of the domain gap between the testing and training data. Existing methods try to solve this issue by reducing the deviation of data distribution, however, they ignore the existence of label deviation in the data due to the acquisition mechanism of the gaze label and the individual physiological differences. In this paper, we first point out that the influence brought by the label deviation cannot be ignored, and propose a gaze label alignment algorithm (GLA) to eliminate the label distribution deviation. Specifically, we first train the feature extractor on all domains to get domain invariant features, and then select an anchor domain to train the gaze regressor. We predict the gaze label on remaining domains and use a mapping function to align the labels. Finally, these aligned labels can be used to train gaze estimation models. Therefore, our method can be combined with any existing method. Experimental results show that our GLA method can effectively alleviate the label distribution shift, and SOTA gaze estimation methods can be further improved obviously.
format Preprint
id arxiv_https___arxiv_org_abs_2412_15601
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Gaze Label Alignment: Alleviating Domain Shift for Gaze Estimation
Zeng, Guanzhong
Wang, Jingjing
Xu, Zefu
Yin, Pengwei
Ren, Wenqi
Xie, Di
Zhu, Jiang
Computer Vision and Pattern Recognition
Gaze estimation methods encounter significant performance deterioration when being evaluated across different domains, because of the domain gap between the testing and training data. Existing methods try to solve this issue by reducing the deviation of data distribution, however, they ignore the existence of label deviation in the data due to the acquisition mechanism of the gaze label and the individual physiological differences. In this paper, we first point out that the influence brought by the label deviation cannot be ignored, and propose a gaze label alignment algorithm (GLA) to eliminate the label distribution deviation. Specifically, we first train the feature extractor on all domains to get domain invariant features, and then select an anchor domain to train the gaze regressor. We predict the gaze label on remaining domains and use a mapping function to align the labels. Finally, these aligned labels can be used to train gaze estimation models. Therefore, our method can be combined with any existing method. Experimental results show that our GLA method can effectively alleviate the label distribution shift, and SOTA gaze estimation methods can be further improved obviously.
title Gaze Label Alignment: Alleviating Domain Shift for Gaze Estimation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2412.15601