Tag
This paper reformulates rank estimation with noisy ordinal labels as a stochastic ordering problem and proposes a learning framework (SOL) that captures ordinal label uncertainty through discriminative and stochastic order losses, achieving reliable rank estimation under various noise types.
Introduces CILN, a framework for generating instance-dependent label noise benchmarks through controlled input corruptions, enabling explicit control over ambiguity source and severity. Experiments show it produces realistic noise structures and exposes failure modes in popular noisy-label learning methods.
This paper proposes a novel active learning framework that leverages foundation model priors to jointly address class imbalance and label noise, achieving over 50% annotation savings compared to baselines across image and text domains.