PriUS enforces uncertainty estimates in segmentation models via evidential learning to match image contrast, corruption levels, and shape complexity, yielding more consistent uncertainty on ACDC, ISIC, and WHS datasets while preserving segmentation accuracy.
Dropout as a bayesian approximation: Representing model uncertainty in deep learning
9 Pith papers cite this work. Polarity classification is still indexing.
9
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
HyperNSD models hypergraph node states as an incidence-aware SDE whose pathwise variability yields competitive uncertainty estimates for OOD and misclassification detection.
B-ACT improves label efficiency in temporal action segmentation by selecting only boundary frames for annotation via a two-stage uncertainty-driven process that fuses neighborhood uncertainty, class ambiguity, and temporal dynamics.
FeFET compute-in-memory Bayesian inference engine with write-free CLT-GRNG achieves 185 TOPS/W/mm² and 640 aJ/sample for uncertainty-aware aerial search and rescue.
A learnable spatial bias term, added to a Noise2Noise-style multi-frame start inside an autoregressive deblurring loop, improves self-supervised defocus deblurring under low-light biased noise.
R-FUML models network outputs as fuzzy memberships, applies entropy-based robust multi-view fusion, and uses memory-effect isolation plus penalties to mitigate view conflicts, outperforming 15 baselines on eight datasets.
TER-DAgger uses force-prediction mismatches to trigger human corrections and residual-policy training, lifting precision-insertion success from 40.0% to 77.2% on average.
ODiSAR uses a Transformer digital twin with reconstruction error and Monte Carlo dropout to detect OOD events in self-adaptive robots, reporting up to 98% AUROC on office navigation and maritime ship tasks.
UMDA combines multi-objective learning with uncertainty modeling for RTA interception and applies distillation to enable single-pass aleatoric plus epistemic uncertainty with 10x inference speedup on JD and Criteo data.
citing papers explorer
-
Principle-Guided Supervision for Interpretable Uncertainty in Medical Image Segmentation
PriUS enforces uncertainty estimates in segmentation models via evidential learning to match image contrast, corruption levels, and shape complexity, yielding more consistent uncertainty on ACDC, ISIC, and WHS datasets while preserving segmentation accuracy.
-
Hypergraph Neural Stochastic Diffusion: An SDE Framework for Uncertainty Estimation
HyperNSD models hypergraph node states as an incidence-aware SDE whose pathwise variability yields competitive uncertainty estimates for OOD and misclassification detection.
-
Boundary-Centric Active Learning for Temporal Action Segmentation
B-ACT improves label efficiency in temporal action segmentation by selecting only boundary frames for annotation via a two-stage uncertainty-driven process that fuses neighborhood uncertainty, class ambiguity, and temporal dynamics.
-
A 185 TOPS/W/mm2 Bayesian Inference Engine with 640 aJ Write-Free FeFET GRNG for Uncertainty-Aware Aerial Search and Rescue
FeFET compute-in-memory Bayesian inference engine with write-free CLT-GRNG achieves 185 TOPS/W/mm² and 640 aJ/sample for uncertainty-aware aerial search and rescue.
-
Physen-Noise2Noise: Physics-Guided Self-Supervised Defocus Deblurring with Bias Correction under Low-Light Conditions
A learnable spatial bias term, added to a Noise2Noise-style multi-frame start inside an autoregressive deblurring loop, improves self-supervised defocus deblurring under low-light biased noise.
-
Robust Fuzzy Multi-view Learning under View Conflict
R-FUML models network outputs as fuzzy memberships, applies entropy-based robust multi-view fusion, and uses memory-effect isolation plus penalties to mitigate view conflicts, outperforming 15 baselines on eight datasets.
-
Force-Aware Residual DAgger via Trajectory Editing for Precision Insertion with Impedance Control
TER-DAgger uses force-prediction mismatches to trigger human corrections and residual-policy training, lifting precision-insertion success from 40.0% to 77.2% on average.
-
Out of Distribution Detection in Self-adaptive Robots with AI-powered Digital Twins
ODiSAR uses a Transformer digital twin with reconstruction error and Monte Carlo dropout to detect OOD events in self-adaptive robots, reporting up to 98% AUROC on office navigation and maritime ship tasks.
-
Uncertainty Modeling for Multi-Objective RTA Interception with Distillation Acceleration
UMDA combines multi-objective learning with uncertainty modeling for RTA interception and applies distillation to enable single-pass aleatoric plus epistemic uncertainty with 10x inference speedup on JD and Criteo data.