AI Paper Atlas

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

SplitNet: Learnable Clean-Noisy Label Splitting for Learning with Noisy Labels

Daehwan Kim, Kwangrok Ryoo, Hansang Cho, Seungryong Kim

IJCV 2024 · Label-efficient and robust learning › Noisy labels · approach: Sample selection and co-training · 24 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 SplitNet (ablation)SplitNet framework · CIFAR-100 90% noiseaccuracy: 33.4 -> 50.7Improved
add SplitNet (ablation)SplitNet framework · CIFAR-100 80% noiseaccuracy: 59.1 -> 70.3Improved
add SplitNet (ablation)SplitNet framework · CIFAR-100 20% noiseaccuracy: 76.8 -> 80.6Improved
add proposed warm-up (K-fold cross-filtering and SSL boosting) (ablation)SplitNet framework · CIFAR-100 90% noiseaccuracy: 41.0 -> 50.7Improved
add proposed warm-up (ablation)SplitNet framework · CIFAR-100 20% noiseaccuracy: 79.8 -> 80.6Improved
add risk hedging (ablation)SplitNet framework · CIFAR-100 90% noiseaccuracy: 46.1 -> 50.7Improved
add risk hedging (ablation)SplitNet framework · CIFAR-100 50% noiseaccuracy: 77.5 -> 77.8Improved
use SplitNet framework instead of DivideMix with FixMatch (ablation)SplitNet · CIFAR-100 90% noiseaccuracy: 26.5 -> 50.7Improved
use dynamic threshold by split confidence instead of fixed 0.5 or 0.95 (ablation)SplitNet SSL · CIFAR-100 90% noisepseudo-label correctnessImproved
include prediction difference as SplitNet input (ablation)SplitNet · CIFAR-100accuracyImproved
use batch normalization in SplitNet (ablation)SplitNet · CIFAR-100convergenceImproved
use 3 layers instead of 2 or 4 in SplitNet (ablation)SplitNet · CIFAR-100accuracyImproved

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