AI Paper Atlas

Research map / Probabilistic and scientific modeling / Uncertainty and Gaussian processes

Revisiting Essential and Nonessential Settings of Evidential Deep Learning

Mengyuan Chen, Junyu Gao, Changsheng Xu

TPAMI 2025 · Probabilistic and scientific modeling › Uncertainty and Gaussian processes · approach: Epistemic versus aleatoric decomposition

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
replace softmax head with projected probability (MSE loss) (ablation)Re-EDL · CIFAR-10 (VGG16) mean OOD detectionAUPR: 81.30 -> 85.46Improved
replace softmax head with projected probability (CE loss) (ablation)Re-EDL · CIFAR-10 (VGG16) mean OOD detectionAUPR: 80.33 -> 84.56Improved
use softplus evidence instead of ReLU (ablation)Re-EDL · CIFAR-10 (VGG16) mean OOD detectionAUPR: 81.81 -> 85.46Improved
use softplus evidence instead of Exp (ablation)Re-EDL · CIFAR-10 (VGG16) mean OOD detectionAUPR: 82.39 -> 85.46Improved
add KL regularization on non-target evidence (ablation)EDL · CIFAR-10 (VGG16) mean OOD detectionAUPR: 84.50 -> 82.32Hurt
add KL regularization on non-target evidence (ablation)Re-EDL · CIFAR-10 (VGG16) mean OOD detectionAUPR: 85.46 -> 83.73Hurt
add KL regularization (R-EDL vs Re-EDL) under Gaussian noise SD 0.200 (ablation)Re-EDL · CIFAR-10 noisy testaverage score: 54.83 -> 57.16Improved
add KL regularization (R-EDL vs Re-EDL) in few-shot 5-way 5-shot (ablation)Re-EDL · mini-ImageNet to CUB OOD-UMAUPR: 83.35 -> 84.22Improved
add small KL coefficient (lg mu -3.0) (ablation)Re-EDL · CIFAR-10 (VGG16) mean OOD detectionAUPR: 85.46 -> 84.41Hurt
add Re-EDL to deep ensemble of 5Deep Ensemble(5) · CIFAR-10 (VGG16) mean OOD detectionAUPR: 84.47 -> 88.35Improved
add Re-EDL to deep ensemble of 25Deep Ensemble(25) · CIFAR-10 (VGG16) mean OOD detectionAUPR: 85.88 -> 88.96Improved
replace EDL with R-EDL (relax prior weight, drop variance term)EDL · CIFAR-10 (VGG16) mean OOD detectionAUPR: 82.32 -> 83.73Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy