Hierarchical Selective Classification
This work addresses uncertainty estimation for deploying neural networks in risk-sensitive applications, presenting an incremental extension to selective classification.
The paper tackles uncertainty estimation in deep neural networks for risk-sensitive tasks by introducing hierarchical selective classification, which leverages class relationships to reduce prediction specificity under uncertainty, and demonstrates that training regimes like CLIP and knowledge distillation improve performance on ImageNet classifiers.
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.