Research map / Label-efficient and robust learning / Domain adaptation and generalization
Contrastive Regression for Domain Adaptation on Gaze Estimation
Yaoming Wang, Yangzhou Jiang, Jin Li, Bingbing Ni, Wenrui Dai, Chenglin Li, Hongkai Xiong, Teng Li
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 |
|---|---|---|---|
| apply CRGA instead of the source-trained baseline | ETH-XGaze-trained model · MPIIGaze | angular gaze error (°): 9.19 -> 5.48 | Improved |
| apply CRGA instead of the source-trained baseline | ETH-XGaze-trained model · RT-GENE | angular gaze error (°): 18.23 -> 11.91 | Improved |
| apply CRGA instead of the source-trained baseline | ETH-XGaze-trained model · GazeCapture | angular gaze error (°): 13.43 -> 5.94 | Improved |
| apply CRGA instead of the source-trained baseline | ETH-XGaze-trained model · EyeDiap | angular gaze error (°): 8.62 -> 5.66 | Improved |
| apply CRGA instead of the source-trained baseline | Gaze360-trained model · MPIIGaze | angular gaze error (°): 8.63 -> 5.89 | Improved |
| apply CRGA instead of the source-trained baseline | Gaze360-trained model · RT-GENE | angular gaze error (°): 23.36 -> 16.23 | Improved |
| apply CRGA instead of the source-trained baseline | Gaze360-trained model · GazeCapture | angular gaze error (°): 9.23 -> 6.19 | Improved |
| apply CRGA instead of the source-trained baseline | Gaze360-trained model · EyeDiap | angular gaze error (°): 8.52 -> 6.49 | Improved |
| add source-domain CDG to the baseline (ablation) | ETH-XGaze-trained model · MPIIGaze | angular gaze error (°): 9.19 -> 6.73 | Improved |
| add target pseudo-label self-training (CSA) without source CDG (ablation) | ETH-XGaze-trained model · MPIIGaze | angular gaze error (°): 9.19 -> 5.37 | Improved |
| add source-domain CDG to the baseline (ablation) | Gaze360-trained model · RT-GENE | angular gaze error (°): 23.36 -> 20.79 | Improved |
| add target pseudo-label self-training (CSA) without source CDG (ablation) | Gaze360-trained model · RT-GENE | angular gaze error (°): 23.36 -> 21.32 | Improved |
Closest papers by meaning
- PureGaze: Purifying Gaze Feature for Generalizable Gaze Estimation (AAAI 2022 · similarity 0.91)
- PnP-GA+: Plug-and-Play Domain Adaptation for Gaze Estimation Using Model Variants (TPAMI 2024 · similarity 0.90)
- Gaze from Origin: Learning for Generalized Gaze Estimation by Embedding the Gaze Frontalization Process (AAAI 2024 · similarity 0.89)
- From Feature to Gaze: A Generalizable Replacement of Linear Layer for Gaze Estimation (CVPR 2024 · similarity 0.88)
- Bootstrap AutoEncoders With Contrastive Paradigm for Self-supervised Gaze Estimation (ICML 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.
