Saved in:
Bibliographic Details
Main Authors: Kim, Younghan, Moon, Kangryun, Park, Yongjun, Kim, Yonggyu
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2408.16964
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909301327527936
author Kim, Younghan
Moon, Kangryun
Park, Yongjun
Kim, Yonggyu
author_facet Kim, Younghan
Moon, Kangryun
Park, Yongjun
Kim, Yonggyu
contents The availability of extensive datasets containing gaze information for each subject has significantly enhanced gaze estimation accuracy. However, the discrepancy between domains severely affects a model's performance explicitly trained for a particular domain. In this paper, we propose the Causal Representation-Based Domain Generalization on Gaze Estimation (CauGE) framework designed based on the general principle of causal mechanisms, which is consistent with the domain difference. We employ an adversarial training manner and an additional penalizing term to extract domain-invariant features. After extracting features, we position the attention layer to make features sufficient for inferring the actual gaze. By leveraging these modules, CauGE ensures that the neural networks learn from representations that meet the causal mechanisms' general principles. By this, CauGE generalizes across domains by extracting domain-invariant features, and spurious correlations cannot influence the model. Our method achieves state-of-the-art performance in the domain generalization on gaze estimation benchmark.
format Preprint
id arxiv_https___arxiv_org_abs_2408_16964
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Causal Representation-Based Domain Generalization on Gaze Estimation
Kim, Younghan
Moon, Kangryun
Park, Yongjun
Kim, Yonggyu
Computer Vision and Pattern Recognition
The availability of extensive datasets containing gaze information for each subject has significantly enhanced gaze estimation accuracy. However, the discrepancy between domains severely affects a model's performance explicitly trained for a particular domain. In this paper, we propose the Causal Representation-Based Domain Generalization on Gaze Estimation (CauGE) framework designed based on the general principle of causal mechanisms, which is consistent with the domain difference. We employ an adversarial training manner and an additional penalizing term to extract domain-invariant features. After extracting features, we position the attention layer to make features sufficient for inferring the actual gaze. By leveraging these modules, CauGE ensures that the neural networks learn from representations that meet the causal mechanisms' general principles. By this, CauGE generalizes across domains by extracting domain-invariant features, and spurious correlations cannot influence the model. Our method achieves state-of-the-art performance in the domain generalization on gaze estimation benchmark.
title Causal Representation-Based Domain Generalization on Gaze Estimation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2408.16964