A Comprehensive Survey on Evidential Deep Learning and Its Applications

J Gao, M Chen, L **ang, C Xu - arxiv preprint arxiv:2409.04720, 2024 - arxiv.org
Reliable uncertainty estimation has become a crucial requirement for the industrial
deployment of deep learning algorithms, particularly in high-risk applications such as …

Recent Advances in OOD Detection: Problems and Approaches

S Lu, Y Wang, L Sheng, A Zheng, L He… - arxiv preprint arxiv …, 2024 - arxiv.org
Out-of-distribution (OOD) detection aims to detect test samples outside the training category
space, which is an essential component in building reliable machine learning systems …

Revisiting Essential and Nonessential Settings of Evidential Deep Learning

M Chen, J Gao, C Xu - arxiv preprint arxiv:2410.00393, 2024 - arxiv.org
Evidential Deep Learning (EDL) is an emerging method for uncertainty estimation that
provides reliable predictive uncertainty in a single forward pass, attracting significant …

Hyper Evidential Deep Learning to Quantify Composite Classification Uncertainty

C Li, K Li, Y Ou, LM Kaplan, A Jøsang, JH Cho… - arxiv preprint arxiv …, 2024 - arxiv.org
Deep neural networks (DNNs) have been shown to perform well on exclusive, multi-class
classification tasks. However, when different classes have similar visual features, it becomes …

Rethinking Out-of-Distribution Detection on Imbalanced Data Distribution

K Liu, Z Fu, S **, C Chen, Z Chen, R Jiang… - arxiv preprint arxiv …, 2024 - arxiv.org
Detecting and rejecting unknown out-of-distribution (OOD) samples is critical for deployed
neural networks to void unreliable predictions. In real-world scenarios, however, the efficacy …

R-EDL: Relaxing Nonessential Settings of Evidential Deep Learning

M Chen, J Gao, C Xu - The Twelfth International Conference on Learning … - openreview.net
A newly-arising uncertainty estimation method named Evidential Deep Learning (EDL),
which can obtain reliable predictive uncertainty in a single forward pass, has garnered …