AI Paper Atlas

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

Maximum Spanning Tree Guided Confidence and Sparse Graph for Robust Noisy Label Learning

Gengfeng Chen, Xu Liu, Boyi Peng, Liangqiu Xiao, Weicheng Xie, Siyang Song, Zitong Yu, Laizhong Cui, Linlin Shen

ECCV 2026 · Label-efficient and robust learning › Noisy labels · approach: Sample selection and co-training · 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 MST-GCSN versus ELR/DULC-style baselinesPreAct ResNet-18 · CIFAR overall averagetest accuracy: 82.2 (DULC) -> 82.6Improved
add MST-GCSN at 90% symmetric noise on CIFAR-100PreAct ResNet-18 · CIFAR-100 (90% sym noise)test accuracy: 54.5 (TCL) -> 56.3Improved
add MST-GCSN at 80-90% sym noise on CIFAR-10PreAct ResNet-18 · CIFAR-10 (80-90% sym noise)test accuracy: DULC 95.0/93.5 vs 94.7/93.2No clear effect
add Confidence-Gated Propagation on MST (ablation)Mixup + CE baseline · CIFAR-10 (90% sym noise)test accuracy: 18.3 -> 63.1Improved
add local label estimate in PLP (ablation)CGP model · CIFAR-10 (90% sym noise)test accuracy: 63.1 -> 83.6Improved
add anchor-guided global label estimate in PLP (ablation)CGP model · CIFAR-10 (90% sym noise)test accuracy: 63.1 -> 81.9Improved
combine local and global estimates in PLP (ablation)CGP model · CIFAR-10 (90% sym noise)test accuracy: 83.6 -> 87.3Improved
add entropy-weighted CE loss (ablation)CGP + PLP · CIFAR-10 (90% sym noise)test accuracy: 87.3 -> 90.9Improved
add entropy-weighted CE loss (ablation)CGP + PLP · CIFAR-100 (50% sym noise)test accuracy: 70.1 -> 73.5Improved
add supervised contrastive loss (ablation)CGP + PLP + WCE · CIFAR-10 (90% sym noise)test accuracy: 90.9 -> 93.2Improved
use MST instead of kNN graph (ablation)graph construction · unreliable edge ratiounreliable edge ratio (%): 10.05 (5-NN) -> 7.10Improved

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