Research map / Label-efficient and robust learning / Domain adaptation and generalization
Improving Few-Shot User-Specific Gaze Adaptation via Gaze Redirection Synthesis
Yu Yu, Gang Liu, Jean-Marc Odobez
Check your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 gaze-redirected training samples during person-specific fine-tuning | GazeNet · ColumbiaGaze, 1/5/9 reference samples | gaze error (°): 5.53 -> 3.92; 3.11 -> 2.88; 2.79 -> 2.60 | Improved |
| Add gaze-redirected training samples during person-specific fine-tuning | GazeNet · MPIIGaze, 1/5/9 reference samples | gaze error (°): 5.28 -> 4.97; 4.64 -> 4.20; 4.31 -> 4.01 | Improved |
| Add gaze-redirection domain adaptation (ablation) | RedFTAdap · ColumbiaGaze, 1/5/9 reference samples | gaze error (°): 4.35 -> 3.92; 3.01 -> 2.88; 2.73 -> 2.60 | Improved |
| Add gaze-redirection domain adaptation (ablation) | RedFTAdap · MPIIGaze, 1/5/9 reference samples | gaze error (°): 4.99 -> 4.97; 4.22 -> 4.20; 4.04 -> 4.01 | Improved |
| Increase gaze redirection range (ablation) | RedFTAdap · MPIIGaze | gaze error (°): 4.15 -> 4.01 | Improved |
| Increase the number of redirected samples per reference beyond about 10 (ablation) | RedFTAdap · MPIIGaze | gaze error (°) | Hurt |
| Fine-tune the generic estimator using only a few person-specific reference samples | GazeNet · ColumbiaGaze and MPIIGaze | gaze error (°): ColumbiaGaze: 3.54 -> 5.53; MPIIGaze: 5.35 -> 5.28 | Mixed |
| Use a convolutional lightness-correction refinement module (ablation) | Gaze redirection and gaze adaptation · Gaze adaptation experiments | gaze error | Hurt |
| Use GAN or CycleGAN for domain adaptation (ablation) | Gaze redirection and gaze adaptation · Gaze adaptation experiments | gaze error | No clear effect |
Closest papers by meaning
- Render-to-Adapt: Unsupervised Personal Adaptation for Gaze Estimation (CVPR 2026 · similarity 0.91)
- Few-Shot Adaptive Gaze Estimation (ICCV 2019 · similarity 0.91)
- Unsupervised Representation Learning for Gaze Estimation (CVPR 2020 · similarity 0.90)
- Alfa: Attentive Low-Rank Filter Adaptation for Structure-Aware Cross-Domain Personalized Gaze Estimation (AAAI 2026 · similarity 0.89)
- Generalizing Gaze Estimation With Outlier-Guided Collaborative Adaptation (ICCV 2021 · similarity 0.89)
- Gaze from Origin: Learning for Generalized Gaze Estimation by Embedding the Gaze Frontalization Process (AAAI 2024 · similarity 0.89)
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.
