AI Paper Atlas

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

MIND: Decoupling Model-Induced Label Noise via Latent Manifold Disentanglement

Dayong Ren

ICML 2026 · Label-efficient and robust learning › Noisy labels · approach: Instance-dependent noise modeling · 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
use global estimation (K=1) instead of multi-subspace estimation (ablation)MIND · S3DIS (PCAM noise)mIoU: 34.08 -> 40.58Improved
add orthogonality loss L_dec to gating (ablation)MIND LDE · S3DIS (PCAM noise)mIoU: 37.38 -> 40.58Improved
add momentum update to basis estimation (ablation)MIND · S3DIS (PCAM noise)mIoU: 38.12 -> 40.58Improved
use MIND instead of CA2Cnoisy-label training · S3DIS PCAMmIoU: 39.36 -> 40.58Improved
use MIND instead of DMLP meta-learningnoisy-label training · S3DIS PCAMmIoU: 37.43 -> 40.58Improved
use GCE robust loss instead of standard CEnoisy-label training · ScanNetV2 PCAMmIoU: 36.40 -> 17.99Hurt
use MIND instead of Standard CEnoisy-label training · S3DIS KPConvmIoU: 63.51 -> 66.48Improved
use MIND for CIFAR transition matrix estimation instead of BLTMIDN estimation · CIFAR-100 (40% IDN)matrix estimation error: 0.35 -> 0.18Improved
use MIND instead of BLTMCIFAR-100 training · CIFAR-100 (40% IDN)accuracy: 43.50 -> 46.22Improved
apply MIND to OpenSeg pseudo-labelsOpenSeg · S3DISmIoU: 43.20 -> 51.34Improved
retrain OpenSeg pseudo-labels with standard CEOpenSeg · S3DISmIoU: 43.20 -> 44.15No clear effect
use MIND instead of CA2C in zero-shot S3DIS to ScanNet transfernoisy-label training · S3DIS->ScanNet PCAMmIoU: 21.50 -> 23.54Improved

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