AI Paper Atlas

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

Dual-Granularity Learning for Regression with Continuous Noisy Labels

Hui GUO, Boyu Wang, Grace Yi

NeurIPS 2026 · Label-efficient and robust learning › Noisy labels · approach: Noise-aware loss and pairwise methods · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Proposes a dual-granularity learning approach for regression with continuous noisy labels, addressing heterogeneous label-noise magnitudes across instances.

Problem

Learning regression models when continuous-valued training labels contain noise whose magnitude varies across instances, a setting less studied than noisy-label classification.

Approach

Uses two granularities of learning to reconcile conflicting needs: sensitivity to label values for correcting small-to-moderate deviations and robustness for large deviations (details not stated in the abstract excerpt).

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use GRAIN dual-granularity training instead of vanilla MSEResNet-50 · UTKFace std_max=60MAE: 9.94 -> 7.54Improved
use GRAIN instead of vanilla MSE under real noiseDenseNet-121 · Bone-AgeMAE: 13.56 -> 12.85Improved
add a histogram (BIN) head to baselinesbaseline methods · UTKFace std_max=60/90MAE: Vanilla 9.94 -> 8.44 (std60); Selfie 8.30 -> 8.44; CoTeaching 7.98 -> 8.29Mixed
stronger data augmentation (GRAIN-AUG)GRAIN · UTKFace std_max=30MAE: 7.01 -> 6.81Improved
noise-robust classification methods (Selfie, CNLCU, CoTeaching) adapted to regressionbaselines · Bone-AgeMAE: Vanilla 13.56 vs Selfie 15.43, CNLCU-S 15.97Hurt
increase label noise from std_max 30 to 90Vanilla · UTKFaceMAE: 8.13 -> 10.25Hurt
ablate residual head, coarse contrastive term, Huber loss, pseudo-label variants (ablation)GRAIN · UTKFaceMAE/RMSE/R2Improved

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