# Semi-Supervised Gaze Estimation via Disentangled Subspace Contrastive Learning

arXiv: https://arxiv.org/abs/2605.27080 · HTML: https://mlsanity.com/paper/2605.27080/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 26 of its 48 references that are in the map.
- First posted on arXiv 26 May 2026.

## Builds on (most cited first, 26 of 26)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Deep Learning Face Attributes in the Wild](https://mlsanity.com/paper/1411.7766/) (2014)
- [FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence](https://mlsanity.com/paper/2001.07685/) (2020)
- [MixMatch: A Holistic Approach to Semi-Supervised Learning](https://mlsanity.com/paper/1905.02249/) (2019)
- [Learning Face Representation from Scratch](https://mlsanity.com/paper/1411.7923/) (2014)
- [Differentiation of Blackbox Combinatorial Solvers](https://mlsanity.com/paper/1912.02175/) (2019)
- [Gaze360: Physically Unconstrained Gaze Estimation in the Wild](https://mlsanity.com/paper/1910.10088/) (2019)
- [CoMatch: Semi-supervised Learning with Contrastive Graph Regularization](https://mlsanity.com/paper/2011.11183/) (2020)
- [Open-World Semi-Supervised Learning](https://mlsanity.com/paper/2102.03526/) (2021)
- [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)
- [Gaze Estimation using Transformer](https://mlsanity.com/paper/2105.14424/) (2021)
- [A Coarse-to-Fine Adaptive Network for Appearance-Based Gaze Estimation](https://mlsanity.com/paper/2001.00187/) (2020)
- [L2CS-Net: Fine-Grained Gaze Estimation in Unconstrained Environments](https://mlsanity.com/paper/2203.03339/) (2022)
- [Class-Aware Contrastive Semi-Supervised Learning](https://mlsanity.com/paper/2203.02261/) (2022)
- [PureGaze: Purifying Gaze Feature for Generalizable Gaze Estimation](https://mlsanity.com/paper/2103.13173/) (2021)
- [Appearance-Based Gaze Estimation Using Dilated-Convolutions](https://mlsanity.com/paper/1903.07296/) (2019)
- [Improving Deep Regression with Ordinal Entropy](https://mlsanity.com/paper/2301.08915/) (2023)
- [Generalizing Gaze Estimation with Outlier-guided Collaborative Adaptation](https://mlsanity.com/paper/2107.13780/) (2021)
- [Weakly-Supervised Physically Unconstrained Gaze Estimation](https://mlsanity.com/paper/2105.09803/) (2021)
- [Semi-Supervised Deep Regression with Uncertainty Consistency and Variational Model Ensembling via Bayesian Neural Networks](https://mlsanity.com/paper/2302.07579/) (2023)
- [CLIP-Gaze: Towards General Gaze Estimation via Visual-Linguistic Model](https://mlsanity.com/paper/2403.05124/) (2024)
- [Enhancing 3D Gaze Estimation in the Wild using Weak Supervision with Gaze Following Labels](https://mlsanity.com/paper/2502.20249/) (2025)
- [RankUp: Boosting Semi-Supervised Regression with an Auxiliary Ranking Classifier](https://mlsanity.com/paper/2410.22124/) (2024)
- [OmniGaze: Reward-inspired Generalizable Gaze Estimation In The Wild](https://mlsanity.com/paper/2510.13660/) (2025)

## Abstract (arXiv)

Appearance-based gaze estimation always suffers from poor generalization due to limited annotated samples and insufficient dataset diversity. Leading approaches adopt weakly supervised learning to generate large-scale pseudo-labeled data from unconstrained real-world scenarios, aiming to mitigate the domain shifts. In this work, we devise a simple yet effective semi-supervised learning architecture that leverages unlabeled data to enhance domain generalization, thereby reducing reliance on labor-intensive manual annotations. Our key insight is to impose Jacobian regularization to disentangle feature representations into discriminative subspaces dedicated to specific gaze components, such as pitch and yaw angles. We further exploit the intrinsic ordinal ranking within each subspace for contrastive learning, enabling the model to learn robust gaze representations from a small set of labeled samples and an abundance of unlabeled ones. This ultimately yields our Disentangled Subspace Contrastive Learning (DSCL) framework. Extensive experiments on multiple benchmarks verify that the proposed DSCL is plug-and-play, achieving competitive performance using only 20%, 10%, and even 5% of the annotated data under both in-domain and cross-domain evaluation settings. The public code is available at hrefhttps://github.com/da60266/DSCLhttps://github.com/da60266/DSCL.