3 papers with code • 0 benchmarks • 0 datasets
How often two shifts of the same image are classified the same
( Image credit: Antialiased CNNs )
These leaderboards are used to track progress in Classification Consistency
Label Distributionally Robust Losses for Multi-class Classification: Consistency, Robustness and Adaptivity
We study a family of loss functions named label-distributionally robust (LDR) losses for multi-class classification that are formulated from distributionally robust optimization (DRO) perspective, where the uncertainty in the given label information are modeled and captured by taking the worse case of distributional weights.
In this work, we focus on semi-supervised learning for video action detection which utilizes both labeled as well as unlabeled data.