AI Paper Atlas

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

LNL+K: Enhancing Learning with Noisy Labels Through Noise Source Knowledge Integration

Siqi Wang, Bryan Plummer

ECCV 2024 · Label-efficient and robust learning › Noisy labels · approach: Noise-aware loss and pairwise methods · 2 citations (OpenAlex)

Read the paper

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 noise source knowledge to CRUST (ablation)CRUST · CIFAR-10 dominant noise 0.8test accuracy: 65.79 -> 80.54Improved
add noise source knowledge to DISC (ablation)DISC · BBBC036 cell datasettest accuracy: 40.55 -> 63.32Improved
apply standard LNL methods (without knowledge) to BBBC036LNL methods · BBBC036test accuracy: 63.49 -> 40.55 (DISC)Hurt
add noise source knowledge to CRUST in selecting clean samples (ablation)CRUST · CIFAR-10 dominant noise 0.8clean-sample recall: 36.15 -> 99.04Improved
add noise source knowledge to FINE on asymmetric noise (ablation)FINE · CIFAR-100 asymmetric noise 0.4test accuracy: 65.11 -> 72.87Improved
add noise source knowledge to CRUST on asymmetric noise (ablation)CRUST · CIFAR-10 asymmetric noise 0.4test accuracy: 89.40 -> 84.96Hurt
add noise source knowledge to SFT on CIFAR-100 dominant noise 0.8 (ablation)SFT · CIFAR-100 dominant noise 0.8test accuracy: 41.76 -> 37.96Hurt
add noise source knowledge to FINE on CHAMMI-CP (ablation)FINE · CHAMMI-CPtest accuracy: 67.27 -> 67.02No clear effect
use partial or incomplete noise source knowledge instead of none (ablation)LNL+K methods · CIFAR-100 dominant noise 0.2test accuracyImproved
estimate noise source knowledge with DualT instead of using ground truth sources (ablation)FINE+k · CIFAR-100 asymmetric noise 0.4test accuracy: 72.87 -> 62.80Hurt
add noise source knowledge to UNICON on Clothing1M (ablation)UNICON · Clothing1Mtest accuracy: 74.56 -> 75.13Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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