AI Paper Atlas

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

Leveraging Dissimilarity Invariance as a Robust Anchor for Learning with Noisy Labels

Wenxiao Fan, Kan Li

AAAI 2026 · Label-efficient and robust learning › Noisy labels · approach: Contrastive learning on noisy data · 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 SNOP (ablation)RoLR + NegScale · CIFAR-100 Sym 80%accuracy: 67.2 -> 70.8Improved
add SNOP (ablation)RoLR + NegScale · CIFAR-10 Sym 50%accuracy: 95.1 -> 96.6Improved
add DCSA (ablation)RoLR + NegScale · CIFAR-100 Sym 80%accuracy: 68.1 -> 70.8Improved
add DCSA (ablation)RoLR + NegScale · CIFAR-10 Sym 80%accuracy: 94.8 -> 95.6Improved
select negatives by pLCA structure instead of random selection (ablation)RoLR + NegScale · CIFAR-100 Sym 80%accuracy: 65.2 -> 70.8Improved
select negatives by pLCA structure instead of random selection (ablation)RoLR + NegScale · CIFAR-10 Sym 50%accuracy: 94.1 -> 96.6Improved
add NegScale to DivideMixDivideMix · CIFAR-100 Sym 80%accuracy: 59.6 -> 70.3Improved
add NegScale to DivideMixDivideMix · CIFAR-10 Sym 80%accuracy: 92.9 -> 94.6Improved
add NegScale to RankMatchRankMatch · CIFAR-100 Sym 80%accuracy: 67.2 -> 70.8Improved
add NegScale to ANNEANNE · CIFAR-100 Sym 80%accuracy: 73.0 -> 73.5Improved
add NegScale to ANNEANNE · CIFAR-10 Sym 80%accuracy: 95.3 -> 96.2Improved
add NegScale to RoLRRoLR · CIFAR-100 Sym 80%accuracy: 66.2 -> 70.8Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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