Conformal prediction is a distribution-free technique for establishing valid
prediction intervals. Although conventionally people conduct conformal
prediction in the output space, this is not the only possibility. In this
paper, we propose feature conformal prediction, which extends the scope of
conformal prediction to semantic feature spaces by leveraging the inductive
bias of deep representation learning. From a theoretical perspective, we
demonstrate that feature conformal prediction provably outperforms regular
conformal prediction under mild assumptions. Our approach could be combined
with not only vanilla conformal prediction, but also other adaptive conformal
prediction methods. Apart from experiments on existing predictive inference
benchmarks, we also demonstrate the state-of-the-art performance of the
proposed methods on large-scale tasks such as ImageNet classification and
Cityscapes image segmentation.

本文提出了基于特征空间的符合性预测方法，利用深度学习的归纳偏差将该方法扩展到语义特征空间，从理论上证明其在温和假设下优于传统方法，并且结合不仅限于普通的符合性预测算法，还可以与其他自适应符合性预测方法结合，从现有的预测推断 benchmark 以及 ImageNet 分类和 Cityscapes 图像分割等大规模任务的实验中证明了该方法的最佳性能。