Sima Behpour

Consistent Robust Adversarial Prediction for General Multiclass Classification

2018 · arXiv (Cornell University)

We propose a robust adversarial prediction framework for general multiclass classification. Our method seeks predictive distributions that robustly optimize non-convex and non-continuous multiclass loss metrics against the worst-case conditional label distributions (the adversarial distributions) that …

Open Ad-hoc Categorization with Contextualized Feature Learning

2025

Adaptive categorization of visual scenes is essential for AI agents to handle changing tasks. Unlike fixed common categories for plants or animals, ad-hoc categories, such as things to sell at a garage sale, are created …