AI Paper Atlas

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

Semi-Supervised Noise Adaptation: Transferring Knowledge from Noise Domain

Yuan Yao, Jin Song, Huixia Li, Tongtong Yuan, Jiaqi Wu, Yu Zhang

ICML 2026 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Statistical transfer learning · 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 NAF (noise domain alignment) to ERMResNet-18 · CIFAR-10top-1 accuracy: 55.55 -> 67.90Improved
add NAF to ERMResNet-50 · CIFAR-10top-1 accuracy: 58.83 -> 73.98Improved
add NAF to ERMResNet-18 · ImageNet-1Kaccuracy: 36.11 -> 37.10Improved
add NAF as plug-in to UDAUDA · CIFAR-10 epoch 20accuracy: 56.11 -> 76.94Improved
add NAF as plug-in to FixMatchFixMatch · CIFAR-10 epoch 20accuracy: 69.40 -> 79.31Improved
add NAF as plug-in to DSTDST · CIFAR-10 epoch 20accuracy: 85.47 -> 85.53No clear effect
add L_n loss (ablation)NAF · CIFAR-100 (4 labels/class)accuracy: 47.33 -> 49.98Improved
add L_n,t loss (ablation)NAF · CIFAR-100 (4 labels/class)accuracy: 40.64 -> 49.98Improved
use NDS alignment instead of Euclidean distance (EDD) (ablation)NAF · CIFAR-100accuracy: 20.03 -> 49.98Improved
give noise class-discriminative structure instead of single point (ablation)NAF · CIFAR-10accuracy: 33.34 -> 58.15Improved
use learned class means instead of fixed class means (ablation)NAF · CIFAR-100accuracy: 46.68 -> 47.72Improved
raise noise dimensionality from 1024 to 2048 (ablation)NAF · CIFAR-100accuracy: 49.98 -> 51.04No clear effect

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