Hierarchical Selective Classification

Shani Goren, Ido Galil, Ran El-Yaniv

Keywords: Hierarchical Selective Classification, Hierarchical Uncertainty, Selective Classification, Non-Bayesian Uncertainty Estimation, CLIP

TL;DR: We extend selective classification to a hierarchical setting, showing outstanding results for various models.

Abstract: Deploying deep neural networks for risk-sensitive tasks necessitates an uncertainty estimation mechanism. This paper introduces *hierarchical selective classification*, extending selective classification to a hierarchical setting. Our approach leverages the inherent structure of class relationships, enabling models to reduce the specificity of their predictions when faced with uncertainty. In this paper, we first formalize hierarchical risk and coverage, and introduce hierarchical risk-coverage curves. Next, we develop algorithms for hierarchical selective classification (which we refer to as "inference rules"), and propose an efficient algorithm that guarantees a target accuracy constraint with high probability. Lastly, we conduct extensive empirical studies on over a thousand ImageNet classifiers, revealing that training regimes such as CLIP, pretraining on ImageNet21k and knowledge distillation boost hierarchical selective performance.

Primary Area: Other (please use sparingly, only use the keyword field for more details)

Submission Number: 9347