Confidence-aware Contrastive Learning for Selective Classification

TL;DR

This paper introduces CCL-SC, a confidence-aware contrastive learning approach that improves selective classification by enhancing feature representations, leading to lower risk and better performance on standard datasets.

Contribution

It provides a theoretical generalization bound for selective classification and proposes a novel feature-level contrastive learning method to improve confidence estimation.

Findings

CCL-SC achieves lower selective risk than state-of-the-art methods.

It improves performance across multiple datasets including CIFAR-10, CIFAR-100, CelebA, and ImageNet.

The method can be combined with existing approaches for further gains.

Abstract

Selective classification enables models to make predictions only when they are sufficiently confident, aiming to enhance safety and reliability, which is important in high-stakes scenarios. Previous methods mainly use deep neural networks and focus on modifying the architecture of classification layers to enable the model to estimate the confidence of its prediction. This work provides a generalization bound for selective classification, disclosing that optimizing feature layers helps improve the performance of selective classification. Inspired by this theory, we propose to explicitly improve the selective classification model at the feature level for the first time, leading to a novel Confidence-aware Contrastive Learning method for Selective Classification, CCL-SC, which similarizes the features of homogeneous instances and differentiates the features of heterogeneous instances, with the strength controlled by the model's confidence. The experimental results on typical datasets, i.e., CIFAR-10, CIFAR-100, CelebA, and ImageNet, show that CCL-SC achieves significantly lower selective risk than state-of-the-art methods, across almost all coverage degrees. Moreover, it can be combined with existing methods to bring further improvement.