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.
翻译:符合预测是一种无分布技术,用于建立有效的预测区间。尽管传统上人们在输出空间中进行符合预测,但这不是唯一的可能性。在本文中,我们提出了特征符合预测,通过利用深度表示学习的归纳偏差,将符合预测的范围扩展到语义特征空间。从理论上讲,我们证明了在温和的假设下,特征符合预测在符合预测之上具有可证明的表现优势。我们的方法不仅可以与香草符合预测相结合,还可以与其他自适应符合预测方法相结合。除了在现有的预测推断基准上进行实验外,我们还展示了所提出方法在大规模任务(如ImageNet分类和城市景观图像分割)中的最先进性能。