AI Paper Atlas

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

CVPR 2022 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Geometric alignment and synthetic-to-real adaptation · 94 citations (OpenAlex)

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 changedWhereMeasuredEffect
apply CRGA instead of the source-trained baselineETH-XGaze-trained model · MPIIGazeangular gaze error (°): 9.19 -> 5.48Improved
apply CRGA instead of the source-trained baselineETH-XGaze-trained model · RT-GENEangular gaze error (°): 18.23 -> 11.91Improved
apply CRGA instead of the source-trained baselineETH-XGaze-trained model · GazeCaptureangular gaze error (°): 13.43 -> 5.94Improved
apply CRGA instead of the source-trained baselineETH-XGaze-trained model · EyeDiapangular gaze error (°): 8.62 -> 5.66Improved
apply CRGA instead of the source-trained baselineGaze360-trained model · MPIIGazeangular gaze error (°): 8.63 -> 5.89Improved
apply CRGA instead of the source-trained baselineGaze360-trained model · RT-GENEangular gaze error (°): 23.36 -> 16.23Improved
apply CRGA instead of the source-trained baselineGaze360-trained model · GazeCaptureangular gaze error (°): 9.23 -> 6.19Improved
apply CRGA instead of the source-trained baselineGaze360-trained model · EyeDiapangular gaze error (°): 8.52 -> 6.49Improved
add source-domain CDG to the baseline (ablation)ETH-XGaze-trained model · MPIIGazeangular gaze error (°): 9.19 -> 6.73Improved
add target pseudo-label self-training (CSA) without source CDG (ablation)ETH-XGaze-trained model · MPIIGazeangular gaze error (°): 9.19 -> 5.37Improved
add source-domain CDG to the baseline (ablation)Gaze360-trained model · RT-GENEangular gaze error (°): 23.36 -> 20.79Improved
add target pseudo-label self-training (CSA) without source CDG (ablation)Gaze360-trained model · RT-GENEangular gaze error (°): 23.36 -> 21.32Improved

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy