Appearance Debiased Gaze Estimation via Stochastic Subject-Wise Adversarial Learning
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866914652578906112 |
|---|---|
| author | Kim, Suneung Nam, Woo-Jeoung Lee, Seong-Whan |
| author_facet | Kim, Suneung Nam, Woo-Jeoung Lee, Seong-Whan |
| contents | Recently, appearance-based gaze estimation has been attracting attention in computer vision, and remarkable improvements have been achieved using various deep learning techniques. Despite such progress, most methods aim to infer gaze vectors from images directly, which causes overfitting to person-specific appearance factors. In this paper, we address these challenges and propose a novel framework: Stochastic subject-wise Adversarial gaZE learning (SAZE), which trains a network to generalize the appearance of subjects. We design a Face generalization Network (Fgen-Net) using a face-to-gaze encoder and face identity classifier and a proposed adversarial loss. The proposed loss generalizes face appearance factors so that the identity classifier inferences a uniform probability distribution. In addition, the Fgen-Net is trained by a learning mechanism that optimizes the network by reselecting a subset of subjects at every training step to avoid overfitting. Our experimental results verify the robustness of the method in that it yields state-of-the-art performance, achieving 3.89 and 4.42 on the MPIIGaze and EyeDiap datasets, respectively. Furthermore, we demonstrate the positive generalization effect by conducting further experiments using face images involving different styles generated from the generative model. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_13865 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Appearance Debiased Gaze Estimation via Stochastic Subject-Wise Adversarial Learning Kim, Suneung Nam, Woo-Jeoung Lee, Seong-Whan Computer Vision and Pattern Recognition Recently, appearance-based gaze estimation has been attracting attention in computer vision, and remarkable improvements have been achieved using various deep learning techniques. Despite such progress, most methods aim to infer gaze vectors from images directly, which causes overfitting to person-specific appearance factors. In this paper, we address these challenges and propose a novel framework: Stochastic subject-wise Adversarial gaZE learning (SAZE), which trains a network to generalize the appearance of subjects. We design a Face generalization Network (Fgen-Net) using a face-to-gaze encoder and face identity classifier and a proposed adversarial loss. The proposed loss generalizes face appearance factors so that the identity classifier inferences a uniform probability distribution. In addition, the Fgen-Net is trained by a learning mechanism that optimizes the network by reselecting a subset of subjects at every training step to avoid overfitting. Our experimental results verify the robustness of the method in that it yields state-of-the-art performance, achieving 3.89 and 4.42 on the MPIIGaze and EyeDiap datasets, respectively. Furthermore, we demonstrate the positive generalization effect by conducting further experiments using face images involving different styles generated from the generative model. |
| title | Appearance Debiased Gaze Estimation via Stochastic Subject-Wise Adversarial Learning |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2401.13865 |