AI Paper Atlas

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

Generalized Regularized Evidential Deep Learning Models: Theory and Comprehensive Evaluation

Deep Shankar Pandey, Hyomin Choi, Qi Yu

TPAMI 2026 · Probabilistic and scientific modeling › Uncertainty and Gaussian processes · approach: Epistemic versus aleatoric decomposition · 1 citations (OpenAlex)

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
add correct evidence regularization (GRED)Exp evidential model · CIFAR-100accuracy (%): 75.76 -> 76.00Improved
add correct evidence regularization (GRED)SELU evidential model · MNISTaccuracy (%): 98.08 -> 98.68Improved
add correct evidence regularization (GRED)SoftPlus evidential model · Tiny-ImageNetaccuracy (%): 90.25 -> 90.63Improved
add correct evidence regularization (GRED)Exp evidential model · CIFAR-10accuracy (%): 95.24 -> 95.44Improved
use ReLU instead of smooth evidential activations (ablation)evidential classifier · CIFAR-10accuracy (%): 95.15 -> 19.50Hurt
add correct evidence regularization (GRED)Exp evidential CodeFormer · CelebA blind face restorationPSNR: 21.46 -> 21.79Improved
add correct evidence regularization (GRED)SELU evidential CodeFormer · CelebA blind face restorationMSE: 514.82 -> 451.93Improved
add uncertainty-guided top-t belief-weighted codebook selection (t=10)GRED-Exp CodeFormer · CelebA blind face restorationPSNR: 21.79 -> 22.33Improved
increase top-t from 5 to 10 (ablation)GRED-Exp CodeFormer · CelebA blind face restorationMSE: 409.64 -> 403.69Improved
add correct evidence regularization (GRED)Exp evidential VPT · 100-way 5-shot CIFAR-100accuracy (%): 49.05 -> 77.00Improved
add correct evidence regularization (GRED)Exp evidential VPT · 100-way 1-shot CIFAR-100accuracy (%): 37.49 -> 46.54Improved
use evidential MSE loss instead of log or Type-II losses (ablation)Exp evidential model · MNISTtest accuracyHurt

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