AI Paper Atlas

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

Noise-Aware Generalization: Robustness to In-Domain Noise and Out-of-Domain Generalization

Siqi Wang, Aoming Liu, Bryan A. Plummer

ICLR 2026 · Label-efficient and robust learning › Noisy labels · approach: Noise-aware loss and pairwise methods · 2 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 DL4ND to ERMERM · OfficeHome (60% symmetric noise)AVG accuracy: 43.2 -> 48.9Improved
add DL4ND to ERM++ERM++ · OfficeHome (60% symmetric noise)AVG accuracy: 52.7 -> 59.8Improved
add DL4ND to SAGMSAGM · PACS (real noise)AVG accuracy: 90.8 -> 93.1Improved
add DL4ND to ERM++ERM++ · PACS (real noise)AVG accuracy: 92.9 -> 93.3Improved
add DL4ND to SAGMSAGM · DomainNet (40% asymmetric noise)ID accuracy: 43.6 -> 52.8Improved
add DL4ND to SAGMSAGM · TerraIncognita (20% asymmetric noise)ID accuracy: 78.2 -> 77.1Hurt
add DL4ND to ERM++ERM++ · OfficeHome (20% asymmetric noise)ID accuracy: 78.5 -> 76.6Mixed
relabel noisy samples instead of removing them (ablation)SAGM+SWAD w/ DL4ND · VLCS (real noise)AVG accuracy: 87.8 -> 90.6Improved
use cross-domain instead of within-domain comparisons for noise detection (ablation)SAGM+SWAD w/ DL4ND · VLCS (real noise)AVG accuracy: 88.2 -> 90.6Improved
build proxies from small-loss samples only (ablation)SAGM+SWAD w/ DL4ND · VLCS (real noise)AVG accuracy: 87.6 -> 90.6Improved
use cross-domain comparisons (ablation)ERM++ w/ DL4ND · CHAMMI-CP (real noise)AVG accuracy: 58.5 -> 58.6No clear effect
build proxies from small-loss samples only (ablation)ERM++ w/ DL4ND · CHAMMI-CP (real noise)AVG accuracy: 56.1 -> 58.6Improved

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