CMRM adds a conformal quantile regularization on prediction margins to any loss, improving noisy-label classification accuracy up to 3.39% across methods and benchmarks while preserving performance at zero noise.
Generalized cross entropy loss for training deep neural networks with noisy labels
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
representative citing papers
The ADC method automates the creation of large image classification datasets using LLMs and search engines, achieving 79% human agreement and reducing label noise on a 1 million image clothing dataset, while also releasing benchmarks for noise and bias issues.
citing papers explorer
-
Conformal Margin Risk Minimization: An Envelope Framework for Robust Learning under Label Noise
CMRM adds a conformal quantile regularization on prediction margins to any loss, improving noisy-label classification accuracy up to 3.39% across methods and benchmarks while preserving performance at zero noise.
-
Automatic Dataset Construction (ADC): Sample Collection, Data Curation, and Beyond
The ADC method automates the creation of large image classification datasets using LLMs and search engines, achieving 79% human agreement and reducing label noise on a 1 million image clothing dataset, while also releasing benchmarks for noise and bias issues.
- Beyond Augmented-Action Surrogates for Multi-Expert Learning-to-Defer