Vacuity-based OOD detection in evidential deep learning is highly sensitive to class cardinality differences between ID and OOD, which can artificially inflate AUROC and AUPR without any change in model predictions.
arXiv preprint arXiv:2007.05566 (2020)
5 Pith papers cite this work, alongside 52 external citations. Polarity classification is still indexing.
5
Pith papers citing it
52
external citations · external index
representative citing papers
A modality-aware post-hoc detector for multi-modal OOD detection in action recognition combines uni-modal prediction relationships with feature-space scores and outperforms prior methods on the MultiOOD benchmark.
Language models show good calibration when asked to estimate the probability that their own answers are correct, with performance improving as models get larger.
Hyperspherical time-frequency representations learned via von Mises-Fisher likelihood improve OOD detection on UCR and UEA archives using k-NN and Mahalanobis scores over contrastive baselines.
JEPA-Indexed Local Expert Growth adds local action corrections for detected shift clusters and yields statistically significant OOD gains on four shift conditions while keeping in-distribution performance intact.
citing papers explorer
-
Rethinking Vacuity for OOD Detection in Evidential Deep Learning
Vacuity-based OOD detection in evidential deep learning is highly sensitive to class cardinality differences between ID and OOD, which can artificially inflate AUROC and AUPR without any change in model predictions.
-
Modality-Aware Out-of-Distribution Detection for Multi-Modal Action Recognition
A modality-aware post-hoc detector for multi-modal OOD detection in action recognition combines uni-modal prediction relationships with feature-space scores and outperforms prior methods on the MultiOOD benchmark.
-
Language Models (Mostly) Know What They Know
Language models show good calibration when asked to estimate the probability that their own answers are correct, with performance improving as models get larger.
-
Learning Hyperspherical Time-Frequency Representations for Time-Series Out-of-Distribution Detection
Hyperspherical time-frequency representations learned via von Mises-Fisher likelihood improve OOD detection on UCR and UEA archives using k-NN and Mahalanobis scores over contrastive baselines.
-
Detecting is Easy, Adapting is Hard: Local Expert Growth for Visual Model-Based Reinforcement Learning under Distribution Shift
JEPA-Indexed Local Expert Growth adds local action corrections for detected shift clusters and yields statistically significant OOD gains on four shift conditions while keeping in-distribution performance intact.