AI Paper Atlas

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

Escaping the Low-Frequency Bias: Adversarial Frequency Perturbation for Generalisable Gaze Estimation

Yang Xu, Feng Lu

ECCV 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
randomly scale source low-frequency amplitudes during trainingResNet-18 baseline · cross-domain average, ResNet-18angular error (deg): 8.54 -> 7.20Improved
remove low-frequency components entirelyResNet-18 baseline · cross-domain average, ResNet-18angular error (deg): 8.54 -> 14.53Hurt
add adversarial low-frequency perturbation (ALFP)ResNet-18 · cross-domain average, ResNet-18angular error (deg): 8.54 -> 6.41Improved
add ALFP to ResNet-50ResNet-50 · cross-domain averageangular error (deg): 8.08 -> 6.15Improved
generate perturbation in spatial domain instead of frequency domain (ablation)ALFP · cross-domain average, ResNet-18angular error (deg): 6.82 -> 6.41Improved
use AdaIN statistics-level mixing instead of element-wise mixing (ablation)ALFP · cross-domain average, ResNet-18angular error (deg): 8.92 -> 6.41Improved
add Lstat batch-level statistical constraint (ablation)ALFP · cross-domain average, ResNet-18angular error (deg): 7.49 -> 6.41Improved
batch-level instead of sample-level Lstat (ablation)ALFP · cross-domain average, ResNet-18angular error (deg): 6.95 -> 6.41Improved
amplitude-domain instead of pixel-domain Lstat (ablation)ALFP · cross-domain average, ResNet-18angular error (deg): 7.26 -> 6.41Improved
range constraint instead of diversity encouragement (ablation)ALFP · cross-domain average, ResNet-18angular error (deg): 7.48 -> 6.41Improved
PGNet adversarial generation instead of within-domain images (ablation)ALFP · cross-domain average, ResNet-18angular error (deg): 6.79 -> 6.41Improved
PGNet adversarial generation instead of 300W-LP images (ablation)ALFP · cross-domain average, ResNet-18angular error (deg): 7.07 -> 6.41Improved

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