AI Paper Atlas

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

Learning with Noisy Labels by Efficient Transition Matrix Estimation to Combat Label Miscorrection

Seong Min Kye, Kwanghee Choi, Joonyoung Yi, Buru Chang

ECCV 2022 · Label-efficient and robust learning › Noisy labels · approach: Instance-dependent noise modeling · 22 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 label correction (ablation)FasTEN · Clothing1Mtop-1 accuracy: 77.07 -> 77.83Improved
add label correction (ablation)FasTEN · CIFAR-10 (sym 80% noise)overall label accuracy: 0.7559 -> 0.7847Improved
add label correction (ablation)FasTEN · CIFAR-10 (sym 80% noise)overall NLL: 1.0057 -> 0.8889Improved
use efficient single-stage transition matrix estimation instead of baselinesFasTEN · CIFAR-10 (sym 80% noise)training time (hours): 10.2 -> 1.54Improved
use FasTEN instead of MSLC at high noiseResNet-34 · CIFAR-10 (sym 80% noise)test accuracy: 64.90 -> 79.52Improved
use FasTEN instead of MSLC at high noiseResNet-34 · CIFAR-100 (sym 80% noise)test accuracy: 21.07 -> 37.36Improved
use FasTEN instead of MSLCResNet-34 · CIFAR-100 (asym 20% noise)test accuracy: 70.86 -> 70.35Hurt
use FasTEN instead of MLaCResNet-34 · CIFAR-10 (asym 40% noise)test accuracy: 90.26 -> 90.43No clear effect
use FasTEN instead of MLaCResNet-50 · Clothing1Mtop-1 accuracy: 75.78 -> 77.83Improved
use FasTEN instead of DivideMixResNet-50 · Clothing1Mtop-1 accuracy: 74.76 -> 77.83Improved

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