SOURCE-LINKED INTELLIGENCE

Selective Posterior Margin Regularization for Forward-Corrected Classification

arXiv · AI, language, vision and robotics · article · Sep 5, 2026 · UTC

Learning with class-conditional label noise often relies on a transition model from latent clean classes to observed annotations. Forward correction embeds this transition in the likelihood, yet finite-sample networks may still memorize corrupted labels. The corrected likelihood also induces a reverse posterior over the clean classes that could explain each annotation. When its leading class differs from the annotation, the model and transition matrix provide evidence against that annotation, but the leading alternatives can remain nearly tied. We introduce Selective Posterior Margin Regulariz

Read original source ↗ Open in workspace

recordType

paper

region

Global