# Appearance Debiased Gaze Estimation via Stochastic Subject-Wise Adversarial Learning

arXiv: https://arxiv.org/abs/2401.13865 · HTML: https://mlsanity.com/paper/2401.13865/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 51 references that are in the map.
- First posted on arXiv 25 Jan 2024.

## Builds on (most cited first, 20 of 20)

- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [Adversarial Discriminative Domain Adaptation](https://mlsanity.com/paper/1702.05464/) (2017)
- [On First-Order Meta-Learning Algorithms](https://mlsanity.com/paper/1803.02999/) (2018)
- [Learning to Generalize: Meta-Learning for Domain Generalization](https://mlsanity.com/paper/1710.03463/) (2017)
- [Interpreting the Latent Space of GANs for Semantic Face Editing](https://mlsanity.com/paper/1907.10786/) (2019)
- [Domain Generalization via Invariant Feature Representation](https://mlsanity.com/paper/1301.2115/) (2013)
- [Domain Generalization for Object Recognition with Multi-task Autoencoders](https://mlsanity.com/paper/1508.07680/) (2015)
- [Gaze360: Physically Unconstrained Gaze Estimation in the Wild](https://mlsanity.com/paper/1910.10088/) (2019)
- [Eye Tracking for Everyone](https://mlsanity.com/paper/1606.05814/) (2016)
- [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)
- [Few-Shot Adaptive Gaze Estimation](https://mlsanity.com/paper/1905.01941/) (2019)
- [A Coarse-to-Fine Adaptive Network for Appearance-Based Gaze Estimation](https://mlsanity.com/paper/2001.00187/) (2020)
- [Appearance-Based Gaze Estimation Using Dilated-Convolutions](https://mlsanity.com/paper/1903.07296/) (2019)
- [Improving Few-Shot User-Specific Gaze Adaptation via Gaze Redirection Synthesis](https://mlsanity.com/paper/1904.10638/) (2019)
- [Generalizing Gaze Estimation with Outlier-guided Collaborative Adaptation](https://mlsanity.com/paper/2107.13780/) (2021)
- [A Differential Approach for Gaze Estimation](https://mlsanity.com/paper/1904.09459/) (2019)
- [Non-Parallel Sequence-to-Sequence Voice Conversion with Disentangled Linguistic and Speaker Representations](https://mlsanity.com/paper/1906.10508/) (2019)
- [End-to-end Video Gaze Estimation via Capturing Head-face-eye Spatial-temporal Interaction Context](https://mlsanity.com/paper/2310.18131/) (2023)
- [Towards Precision in Appearance-based Gaze Estimation in the Wild](https://mlsanity.com/paper/2302.02353/) (2023)

## Built on by (most cited first, 3 of 3)

- [CapStARE: Capsule-based Sequential Architecture for Robust and Efficient Gaze Estimation](https://mlsanity.com/paper/2509.19936/) (2025)
- [GMGaze: MoE-Based Context-Aware Gaze Estimation with CLIP and Multiscale Transformer](https://mlsanity.com/paper/2605.00799/) (2026)
- [LISA: Language-guided Interference-aware Spatial-Frequency Attention for Driver Gaze Estimation](https://mlsanity.com/paper/2605.17287/) (2026)

## Abstract (arXiv)

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.