AI Paper Atlas

Research map / Label-efficient and robust learning / Noisy labels

See Through the Noise: Improving Domain Generalization in Gaze Estimation

Yanming Peng, Shijing Wang, Yaping Huang, Yi Tian

CVPR 2026 · Label-efficient and robust learning › Noisy labels · approach: Loss correction and noise robustness theory · 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
add SeeTN (noise-robust semantic manifold regularization)ResNet-18 · ETH-XGaze to MPIIFaceGazemean angular error: 8.07 -> 6.58Improved
add SeeTNResNet-18 · Within Gaze360mean angular error: 11.14 -> 10.73Improved
add L_align^C (clean-sample affinity alignment) (ablation)SeeTN, ResNet-18 · ETH-XGaze to MPIIFaceGazemean angular error: 8.07 -> 7.14Improved
add L_align^N (noisy-sample affinity regularization) (ablation)SeeTN, ResNet-18 · ETH-XGaze to MPIIFaceGazemean angular error: 7.14 -> 6.58Improved
add L_align^N (ablation)SeeTN, ResNet-18 · Gaze360 to EyeDiapmean angular error: 8.11 -> 7.57Improved
add prototype-based semantic manifold (ablation)SeeTN, ResNet-18 · ETH-XGaze to MPIIFaceGazemean angular error: 7.88 -> 6.58Improved
use cosine similarity instead of L2 distance (ablation)SeeTN, ResNet-18 · ETH-XGaze to MPIIFaceGazemean angular error: 7.01 -> 6.58Improved
use affinity-mismatch indicator eta instead of L1 loss for noisy sample detection (ablation)SeeTN, ResNet-18 · ETH-XGaze to MPIIFaceGazemean angular error: 7.73 -> 6.58Improved
increase number of prototypes K from 12 to 16 (ablation)SeeTN, ResNet-18 · ETH-XGaze to MPIIFaceGazemean angular error: 6.58 -> 7.59Hurt
decrease prototypes K from 12 to 8 (ablation)SeeTN, ResNet-18 · ETH-XGaze to MPIIFaceGazemean angular error: 6.58 -> 7.37Hurt
increase noisy ratio t from 5% to 20% (ablation)SeeTN, ResNet-18 · ETH-XGaze to MPIIFaceGazemean angular error: 6.58 -> 7.63Hurt
raise loss weight lambda from 0.1 to 1 (ablation)SeeTN, ResNet-18 · ETH-XGaze to MPIIFaceGazemean angular error: 6.58 -> 7.02Hurt

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