arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2409.04720cs.LGcs.AI
收藏

证据深度学习及其应用综述

A Comprehensive Survey on Evidential Deep Learning and Its Applications

Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所);School of Artificial Intelligence, University of Chinese Academy of Sciences(中国科学院大学人工智能学院);Peng Cheng Laboratory(鹏城实验室)

Junyu Gao, Mengyuan Chen, Liangyu Xiang, Changsheng Xu

AI总结:

本文综述证据深度学习(EDL)的理论基础、四类技术进展、跨范式应用及未来方向,突出其单次前向传播即可低成本估计不确定性的优势。

摘要:

可靠的不确定性估计已成为深度学习算法工业部署的一项关键需求,尤其是在自动驾驶和医疗诊断等高风险应用中。然而,基于深度集成或贝叶斯神经网络的主流不确定性估计方法通常会带来巨大的计算开销。为应对这一挑战,一种名为证据深度学习(Evidential Deep Learning,EDL)的新型范式已经出现,它只需一次前向传播并以极少的额外计算即可提供可靠的不确定性估计。本综述全面概述了当前关于 EDL 的研究,旨在不要求读者具备先验知识的情况下,为其提供该领域的广泛入门介绍。具体而言,我们首先深入探讨 EDL 的理论基础,即主观逻辑理论,并讨论它与其他不确定性估计框架的区别。随后,我们从四个方面介绍 EDL 现有的理论进展:重构证据收集过程、通过 OOD 样本改进不确定性估计、探究各种训练策略,以及证据回归网络。此后,我们详细阐述其在多种机器学习范式和下游任务中的广泛应用。最后,本文展望了提升 EDL 性能并推动其更广泛采用的未来方向,并强调了潜在的研究途径。

英文摘要:

Reliable uncertainty estimation has become a crucial requirement for the industrial deployment of deep learning algorithms, particularly in high-risk applications such as autonomous driving and medical diagnosis. However, mainstream uncertainty estimation methods, based on deep ensembling or Bayesian neural networks, generally impose substantial computational overhead. To address this challenge, a novel paradigm called Evidential Deep Learning (EDL) has emerged, providing reliable uncertainty estimation with minimal additional computation in a single forward pass. This survey provides a comprehensive overview of the current research on EDL, designed to offer readers a broad introduction to the field without assuming prior knowledge. Specifically, we first delve into the theoretical foundation of EDL, the subjective logic theory, and discuss its distinctions from other uncertainty estimation frameworks. We further present existing theoretical advancements in EDL from four perspectives: reformulating the evidence collection process, improving uncertainty estimation via OOD samples, delving into various training strategies, and evidential regression networks. Thereafter, we elaborate on its extensive applications across various machine learning paradigms and downstream tasks. In the end, an outlook on future directions for better performances and broader adoption of EDL is provided, highlighting potential research avenues.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑