AI Paper Atlas

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

Content Diversity-guided Ambiguity Mitigation for Open-Set Noisy Label Learning

Zhihao Zhou, Rui Li, Xueying Li

AAAI 2026 · Label-efficient and robust learning › Noisy labels · approach: Noise-aware loss and pairwise methods · 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 content diversity-guided semantic synchronization (CDgss) (ablation)DivideMix · CIFAR-10 (10k OOD)accuracy: 92.73 -> 94.66Improved
add CDgss (ablation)DivideMix · TinyImageNet OOD (10k)accuracy: 70.38 -> 77.09Improved
add region-sensitive distillation regularization (RSDR) on top of CDgss (ablation)CDgAM · CIFAR-10 (10k OOD)accuracy: 94.66 -> 95.82Improved
add RSDR on top of CDgss (ablation)CDgAM · TinyImageNet OOD (10k)accuracy: 77.09 -> 77.54Improved
add RSDR on top of CDgss (ablation)CDgAM · TinyImageNet OOD (20k)accuracy: 75.85 -> 77.33Improved
use GPT-4o class descriptions instead of random text (ablation)CDgAM · CIFAR-10 (10k CIFAR-100 OOD)accuracy: 93.86 -> 95.82Improved
use GPT-4o descriptions instead of class names only (ablation)CDgAM · CIFAR-10 (10k CIFAR-100 OOD)accuracy: 95.28 -> 95.82Improved
use GPT-4o instead of DeepSeek-V2 for descriptions (ablation)CDgAM · CIFAR-10 (10k CIFAR-100 OOD)accuracy: 95.65 -> 95.82Improved
increase number of generated descriptions L beyond 5 (ablation)CDgAM · CIFAR-10/100accuracyNo clear effect
raise RSDR coefficient lambda beyond 1 (ablation)CDgAM · CIFAR-10/100accuracyHurt
use CDgAM instead of SEDSED · CIFAR-100N sym-80%accuracy: 38.15 -> 48.61Improved
use CDgAM instead of SEDSED · WebFG-496 Web-caraccuracy: 88.88 -> 90.89Improved

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