AI Paper Atlas

Research map / Label-efficient and robust learning / Domain adaptation and generalization

Towards Privacy-Protected Generalized Gaze Estimation Using Diffusion Models and Domain Stability Adaptation Framework

Ziyi Wang, Shengcheng Ye, Faming Fang, Haichuan Song

AAAI 2026 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Geometric alignment and synthetic-to-real adaptation · 0 citations (OpenAlex)

Read the paperCheck 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
fine-tune on synthetic gaze data (10000 DDPM+LDM images) (ablation)PureGaze · Average over 4 cross-dataset tasksangular error (deg): 8.29 -> 6.93Improved
increase number of synthetic fine-tuning images (D+L) (ablation)PureGaze · Average over 4 cross-dataset tasksangular error (deg): 7.60 (1000) -> 7.33 (5000) -> 6.93 (10000)Improved
mix DDPM-Gaze and LDM-Gaze data instead of one source (10000 images) (ablation)PureGaze fine-tuning · Average over 4 cross-dataset tasksangular error (deg): 7.26 (D) / 7.28 (L) -> 6.93 (D+L)Improved
use DSA variance constraint over N=4 same-label images instead of plain fine-tuning (N=1) (ablation)PureGaze · Average over 4 cross-dataset tasksangular error (deg): 6.93 -> 6.55Improved
add DSA to Gaze360 modelGaze360 UDA model · DG->DDangular error (deg): 8.77 -> 7.77Improved
add DSA instead of plain synthetic fine-tuning to UnReGA-UnReGA- · DG->DMangular error (deg): 5.58 -> 5.13 (fine-tuning: 5.58)Improved
add plain fine-tuning on synthetic data to Gaze360 model on source-to-source taskGaze360 UDA model · DG->DM->DGangular error (deg): 14.43 -> 14.34No clear effect
use DSA vs best DG baseline GFALDSA · ETH-XGaze -> MPIIGazeangular error (deg): 5.72 -> 6.12Hurt
use 1000 DDPM-Gaze images only (small amount) for fine-tuning on ETH->EyeDiap (ablation)PureGaze · ETH-XGaze -> EyeDiapangular error (deg): 7.48 -> 7.33Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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