Introduces Relative Geometric Conflict (RGC) using gradient direction comparison and empirical Fisher trace factorization to improve reliability estimation beyond loss or confidence signals in noisy-label training.
How does disagreement help generalization against label corruption? InInternational conference on machine learning, pages 7164–7173
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Radial-Angular Geometry for Reliable Update Diagnosis in Noisy-Label Learning
Introduces Relative Geometric Conflict (RGC) using gradient direction comparison and empirical Fisher trace factorization to improve reliability estimation beyond loss or confidence signals in noisy-label training.