AI Paper Atlas

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

De-confounded Gaze Estimation

Ziyang Liang, Yiwei Bao, Feng Lu

ECCV 2024 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Augmentation and mixture-of-experts generalization · 7 citations (OpenAlex)

Read the paper

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 FSCI causal intervention framework to ResNet18ResNet18 gaze estimator · DE->DMangular error (deg): 9.07 -> 5.79Improved
add Causal Intervention Module on top of Feature Separation Module (ablation)FSCI-ResNet18 · DE->DMangular error (deg): 7.67 -> 5.79Improved
use cross-attention Feature Separation Module instead of three separate ResNet18 (ablation)FSCI-ResNet18 · DE->DMangular error (deg): 8.72 -> 5.79Improved
apply FSCI to a ResNet50 backboneResNet50 · DG->DDangular error (deg): 11.83 -> 10.20Improved
add CIM to FSCI-ResNet50 (versus w/o CIM) (ablation)FSCI-ResNet50 · DE->DDangular error (deg): DE->DD 7.23 -> 6.68; DE->DM 6.17 -> 5.47Mixed
use FSM with separate ResNet50x3 instead of cross-attention separation (ablation)FSCI-ResNet50 · DG->DDangular error (deg): 10.20 -> 12.99Hurt
use Dynamic Confounder Bank instead of confounder dictionary (ablation)FSCI · DE->DMangular error (deg): 5.77 -> 5.79 (best dictionary vs FSCI)No clear effect
use Dynamic Confounder Bank instead of confounder dictionary (ablation)FSCI · DE->DDangular error (deg): 8.18 -> 6.96Improved
apply Gaussian noise (std 0.2) to input; compare FSCI to baseline robustnessFSCI vs ResNet18 · DE->DMerror increase (deg): 4.13 -> 1.29Improved
apply causal intervention to reduce head-pose-to-gaze spurious correlationFSCI · DE->DM, complexion groupserror difference between complexions: 1.26 vs 0.72 deg differenceImproved

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