Research map / Label-efficient and robust learning / Domain adaptation and generalization
PureGaze: Purifying Gaze Feature for Generalizable Gaze Estimation
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Add self-adversarial feature purification | Baseline · Gaze360→MPIIGaze | angular error: 9.89° -> 9.28° | Helped |
| Add self-adversarial feature purification | Baseline · Gaze360→EyeDiap | angular error: 11.42° -> 9.32° | Helped |
| Add self-adversarial feature purification | Baseline · ETH-XGaze→MPIIGaze | angular error: 8.13° -> 7.08° | Helped |
| Add self-adversarial feature purification | Baseline · ETH-XGaze→EyeDiap | angular error: 7.74° -> 7.48° | Helped |
| Apply the self-adversarial framework to CA-Net | CA-Net · Gaze360→MPIIGaze | angular error: 27.13° -> 9.03° | Helped |
| Apply the self-adversarial framework to CA-Net | CA-Net · Gaze360→EyeDiap | angular error: 31.41° -> 9.71° | Helped |
| Apply the self-adversarial framework to Full-Face | Full-Face · Gaze360→MPIIGaze | angular error: 11.13° -> 9.16° | Helped |
| Apply the self-adversarial framework to Full-Face | Full-Face · ETH-XGaze→MPIIGaze | angular error: 12.35° -> 11.50° | Helped |
| Apply the self-adversarial framework to Full-Face | Full-Face · ETH-XGaze→EyeDiap | angular error: 30.15° -> 21.01° | Helped |
| Add LP-Loss (ablation) | PureGaze · Cross-dataset gaze estimation | angular error | Helped |
| Add TA-Loss (ablation) | PureGaze · Cross-dataset gaze estimation | angular error | Helped |
| Set TA-Loss threshold k to 0.75 (ablation) | PureGaze · Cross-dataset gaze estimation | angular error | Helped |
Closest papers by meaning
- From Feature to Gaze: A Generalizable Replacement of Linear Layer for Gaze Estimation (CVPR 2024 · similarity 0.90)
- Gaze from Origin: Learning for Generalized Gaze Estimation by Embedding the Gaze Frontalization Process (AAAI 2024 · similarity 0.90)
- OmniGaze: Reward-inspired Generalizable Gaze Estimation in the Wild (NeurIPS 2025 · similarity 0.88)
- Enhancing 3D Gaze Estimation in the Wild using Weak Supervision with Gaze Following Labels (CVPR 2025 · similarity 0.88)
- CLIP-Gaze: Towards General Gaze Estimation via Visual-Linguistic Model (AAAI 2024 · similarity 0.88)
- Gaze Label Alignment: Alleviating Domain Shift for Gaze Estimation (AAAI 2025 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.