Lune

NeurIPS2024Top-tier venue

Hyper-opinion Evidential Deep Learning for Out-of-Distribution Detection

Jingen Qu, Yufei Chen, Xiaodong Yue, Wei Fu, Qiguang Huang

Abstract

Evidential Deep Learning (EDL), grounded in Evidence Theory and Subjective Logic (SL), provides a robust framework to estimate uncertainty for out-of-distribution (OOD) detection alongside traditional classification probabilities. However, the EDL framework is constrained by its focus on evidence that supports only single categories, neglecting the other collective evidences that could corroborate multiple in-distribution categories. This limitation leads to a diminished estimation of uncertainty and a subsequent decline in OOD detection performance. Additionally, EDL encounters the vanishing gradient problem within its fully-connected layers, further degrading classification accuracy. To address these issues, we introduce hyper-domain and propose Hyper-opinion Evidential Deep Learning (HEDL). HEDL extends the evidence modeling paradigm by explicitly integrating sharp evidence, which supports a singular category, with vague evidence that accommodates multiple potential categories. Additionally, we propose a novel opinion projection mechanism that translates hyper-opinion into multinomial-opinion, which is then optimized within the EDL framework to ensure precise classification and refined uncertainty estimation. HEDL integrates evidences across various categories to yield a holistic evidentiary foundation for achieving superior OOD detection. Furthermore, our proposed opinion projection method effectively mitigates the vanishing gradient issue, ensuring classification accuracy without additional model complexity. Extensive experiments over many datasets demonstrate our proposed method outperforms existing OOD detection methods.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

6 top-tier papers have cited it since. Know what they found before your reviewers do.

Questions to start from

Lune can draw on

the full paper · the top-tier papers that cite it · related work

Get the answer

Free to start. No credit card required.

Lineage

  • Stop Guessing: Choosing the Optimization-Consistent Uncertainty Measurement for Evidential Deep Learning cites Vicinal Label Supervision for Reliable Aleatoric and Epistemic Uncertainty Estimation
  • ReAct: Out-of-distribution Detection With Rectified Activations cites Energy-based Out-of-distribution Detection
  • Out-of-Distribution Detection with Deep Nearest Neighbors cites Energy-based Out-of-distribution Detection
  • Out-of-Distribution Detection with Deep Nearest Neighbors cites ReAct: Out-of-distribution Detection With Rectified Activations
Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers6

  1. Vicinal Label Supervision for Reliable Aleatoric and Epistemic Uncertainty EstimationLinye Li, Yufei Chen, Xiaodong YueNeurIPS 2025 · 3 citations
  2. Robust Adversarial Quantification via Conflict-Aware Evidential Deep LearningCharmaine Barker, Daniel Bethell, Simos GerasimouICLR 2026 · 2 citations
  3. Hyper-Opinion Vagueness Quantification for Robust Multimodal LearningDisen Hu, Xun Jiang, Xiaofeng Cao, Zheng Wang et al.AAAI 2026 · 1 citation
  4. BD-Merging: Bias-Aware Dynamic Model Merging with Evidence-Guided Contrastive LearningYuhan Xie, Chen LyuCVPR 2026
  5. Stop Guessing: Choosing the Optimization-Consistent Uncertainty Measurement for Evidential Deep LearningLinye Li, Yufei Chen, Xiaodong Yue, Xujing Zhou et al.ICLR 2026

Builds on34

  1. Energy-based Out-of-distribution DetectionWeitang Liu, Xiaoyun Wang, John D. Owens, Yixuan LiNeurIPS 2020 · 2,213 citations
  2. Out-of-Distribution Detection with Deep Nearest NeighborsYiyou Sun, Yifei Ming, Xiaojin Zhu, Yixuan LiICML 2022 · 789 citations
  3. Deep Evidential RegressionAlexander Amini, Wilko Schwarting, Ava Soleimany, Daniela RusNeurIPS 2020 · 777 citations
  4. CSI: Novelty Detection via Contrastive Learning on Distributionally Shifted InstancesJihoon Tack, Sangwoo Mo, Jongheon Jeong, Jinwoo ShinNeurIPS 2020 · 755 citations
  5. ReAct: Out-of-distribution Detection With Rectified ActivationsYiyou Sun, Chuan Guo, Yixuan LiNeurIPS 2021 · 733 citations

Related papers

  1. Uncertainty Estimation by Density Aware Evidential Deep LearningTaeseong Yoon, Heeyoung KimICML 2024 · 16 citations
  2. Hyper Evidential Deep Learning to Quantify Composite Classification UncertaintyChangbin Li, Kangshuo Li, Yuzhe Ou, Lance M. Kaplan et al.ICLR 2024 · 10 citations
  3. R-EDL: Relaxing Nonessential Settings of Evidential Deep LearningMengyuan Chen, Junyu Gao, Changsheng XuICLR 2024 · 18 citations
  4. Multidimensional Uncertainty-Aware Evidential Neural NetworksYibo Hu, Yuzhe Ou, Xujiang Zhao, Jin-Hee Cho et al.AAAI 2021 · 32 citations
  5. Towards Evidential and Class Separable Open Set Object DetectionRuofan Wang, Rui-Wei Zhao, Xiaobo Zhang, Rui FengAAAI 2024 · 12 citations
Dusk over the sea between two cliffs drawn in fine vertical lines