# See Through the Noise: Improving Domain Generalization in Gaze Estimation

arXiv: https://arxiv.org/abs/2604.16562 · HTML: https://mlsanity.com/paper/2604.16562/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 22 of its 41 references that are in the map.
- First posted on arXiv 17 Apr 2026.

## Builds on (most cited first, 22 of 22)

- [Identity Mappings in Deep Residual Networks](https://mlsanity.com/paper/1603.05027/) (2016)
- [DivideMix: Learning with Noisy Labels as Semi-supervised Learning](https://mlsanity.com/paper/2002.07394/) (2020)
- [How does Disagreement Help Generalization against Label Corruption?](https://mlsanity.com/paper/1901.04215/) (2019)
- [WebVision Database: Visual Learning and Understanding from Web Data](https://mlsanity.com/paper/1708.02862/) (2017)
- [CleanNet: Transfer Learning for Scalable Image Classifier Training with Label Noise](https://mlsanity.com/paper/1711.07131/) (2017)
- [Gaze360: Physically Unconstrained Gaze Estimation in the Wild](https://mlsanity.com/paper/1910.10088/) (2019)
- [Appearance-Based Gaze Estimation in the Wild](https://mlsanity.com/paper/1504.02863/) (2015)
- [ETH-XGaze: A Large Scale Dataset for Gaze Estimation under Extreme Head Pose and Gaze Variation](https://mlsanity.com/paper/2007.15837/) (2020)
- [It's Written All Over Your Face: Full-Face Appearance-Based Gaze Estimation](https://mlsanity.com/paper/1611.08860/) (2016)
- [MPIIGaze: Real-World Dataset and Deep Appearance-Based Gaze Estimation](https://mlsanity.com/paper/1711.09017/) (2017)
- [Appearance-based Gaze Estimation With Deep Learning: A Review and Benchmark](https://mlsanity.com/paper/2104.12668/) (2021)
- [A Coarse-to-Fine Adaptive Network for Appearance-Based Gaze Estimation](https://mlsanity.com/paper/2001.00187/) (2020)
- [Robust Bi-Tempered Logistic Loss Based on Bregman Divergences](https://mlsanity.com/paper/1906.03361/) (2019)
- [PureGaze: Purifying Gaze Feature for Generalizable Gaze Estimation](https://mlsanity.com/paper/2103.13173/) (2021)
- [Training Convolutional Networks with Noisy Labels](https://mlsanity.com/paper/1406.2080/) (2014)
- [Towards Understanding Deep Learning from Noisy Labels with Small-Loss Criterion](https://mlsanity.com/paper/2106.09291/) (2021)
- [Gaze-Contingent Ocular Parallax Rendering for Virtual Reality](https://mlsanity.com/paper/1906.09740/) (2019)
- [Deep semantic gaze embedding and scanpath comparison for expertise classification during OPT viewing](https://mlsanity.com/paper/2003.13987/) (2020)
- [Fine-Grained Classification with Noisy Labels](https://mlsanity.com/paper/2303.02404/) (2023)
- [Learning with Noisy labels via Self-supervised Adversarial Noisy Masking](https://mlsanity.com/paper/2302.06805/) (2023)
- [LatentGaze: Cross-Domain Gaze Estimation through Gaze-Aware Analytic Latent Code Manipulation](https://mlsanity.com/paper/2209.10171/) (2022)
- [Suppressing Uncertainty in Gaze Estimation](https://mlsanity.com/paper/2412.12890/) (2024)

## Abstract (arXiv)

Generalizable gaze estimation methods have garnered increasing attention due to their critical importance in real-world applications and have achieved significant progress. However, they often overlook the effect of label noise, arising from the inherent difficulty of acquiring precise gaze annotations, on model generalization performance. In this paper, we are the first to comprehensively investigate the negative effects of label noise on generalization in gaze estimation. Further, we propose a novel solution, called See-Through-Noise (SeeTN) framework, which improves generalization from a novel perspective of mitigating label noise. Specifically, we propose to construct a semantic embedding space via a prototype-based transformation to preserve a consistent topological structure between gaze features and continuous labels. We then measure feature-label affinity consistency to distinguish noisy from clean samples, and introduce a novel affinity regularization in the semantic manifold to transfer gaze-related information from clean to noisy samples. Our proposed SeeTN promotes semantic structure alignment and enforces domain-invariant gaze relationships, thereby enhancing robustness against label noise. Extensive experiments demonstrate that our SeeTN effectively mitigates the adverse impact of source-domain noise, leading to superior cross-domain generalization without compromising the source-domain accuracy, and highlight the importance of explicitly handling noise in generalized gaze estimation.