Pith. sign in

REVIEW 17 cited by

What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 1703.04977 v2 pith:3LXU4WOX submitted 2017-03-15 cs.CV

What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?

classification cs.CV
keywords uncertaintybayesiandeepepistemiclearningaleatoricmodeltasks
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

There are two major types of uncertainty one can model. Aleatoric uncertainty captures noise inherent in the observations. On the other hand, epistemic uncertainty accounts for uncertainty in the model -- uncertainty which can be explained away given enough data. Traditionally it has been difficult to model epistemic uncertainty in computer vision, but with new Bayesian deep learning tools this is now possible. We study the benefits of modeling epistemic vs. aleatoric uncertainty in Bayesian deep learning models for vision tasks. For this we present a Bayesian deep learning framework combining input-dependent aleatoric uncertainty together with epistemic uncertainty. We study models under the framework with per-pixel semantic segmentation and depth regression tasks. Further, our explicit uncertainty formulation leads to new loss functions for these tasks, which can be interpreted as learned attenuation. This makes the loss more robust to noisy data, also giving new state-of-the-art results on segmentation and depth regression benchmarks.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 17 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Quantifying Consistency in LLM Logical Reasoning via Structural Uncertainty

    cs.AI 2026-06 unverdicted novelty 7.0

    Structural uncertainty from self-preference-induced rankings of LLM reasoning paths complements answer dispersion for identifying unreliable instances on logical tasks while collapsing on factual retrieval.

  2. Toward Calibrated, Fair, and accurate Deepfake Detection

    cs.LG 2026-06 unverdicted novelty 7.0

    Face-Feature Tuning is a label-free logit remapping method that reduces FPR/TPR gaps across groups in deepfake detection while preserving overall accuracy.

  3. Reconstructing the Stripping History of the Sagittarius Stream with Neural Networks

    astro-ph.GA 2026-05 unverdicted novelty 7.0

    A neural network trained on simulations infers stripping times for Sagittarius stream stars from phase-space data, measuring a 0.3 dex/Gyr metallicity gradient and estimating ages for globular clusters such as Pal 12 ...

  4. ElemeNet: Multiscale Molecular Machine Learning with Uncertainty Quantification Across the Periodic Table

    physics.chem-ph 2026-06 unverdicted novelty 6.0

    ElemeNet is a unified ML software package for molecular property prediction across elements 1-100 with built-in uncertainty quantification and competitive benchmarks on diverse chemistry datasets.

  5. MoPe: Motion Permanence for Robust Monocular Gaussian Mapping in Dynamic Environments

    cs.RO 2026-06 unverdicted novelty 6.0

    MoPe propagates historical dynamic posteriors via SE(3) warping and bounded Bayesian fusion to maintain persistent motion state in monocular Gaussian SLAM.

  6. On the QUEST for Uncertainty Quantification via Highest Density Regions

    cs.LG 2026-06 unverdicted novelty 6.0

    QUEST measures uncertainty via the Lebesgue volume of highest-density regions of a distribution's support, evaluated at robustness parameter alpha, and claims to satisfy UQ axioms while outperforming variance and diff...

  7. TwinSpecNet: Extending APOGEE's chemical reach to low-S/N spectra via empirical paired learning

    astro-ph.GA 2026-04 unverdicted novelty 6.0

    TwinSpecNet uses empirical paired learning on spectral twins to denoise low-S/N APOGEE spectra and predict stellar parameters and abundances with lower scatter than the standard pipeline.

  8. Ensemble-Based Uncertainty Estimation for Code Correctness Estimation

    cs.SE 2026-03 unverdicted novelty 6.0

    Ensemble Semantic Entropy improves correlation with code correctness over single-model methods and powers a cascading scaling system that cuts FLOPs by 64.9% while preserving performance on LiveCodeBench.

  9. Low Rank Based Subspace Inference for the Laplace Approximation of Bayesian Neural Networks

    cs.LG 2025-02 unverdicted novelty 6.0

    Derives optimal low-rank subspace for Laplace approx in BNNs, provides scalable outperforming version, and new comparison metric.

  10. RoboMD: Uncovering Robot Vulnerabilities through Semantic Potential Fields

    cs.RO 2024-12 unverdicted novelty 6.0

    A deep RL vulnerability-prediction policy trained in semantic embedding space finds up to 23% more unique robot manipulation failures than vision-language baselines and enables more efficient fine-tuning.

  11. From 3D Perception to Safety Reasoning: A Graph-Based Framework for Real-Time Underground Mine Monitoring

    cs.CV 2026-06 unverdicted novelty 5.0

    A graph-structured framework fuses 3D perception with rule-based, LLM, and memory reasoning to raise hazard coverage from 57% to 93% across 115 simulated underground mine scenarios.

  12. Multi-Agent Reinforcement Learning for Safe Autonomous Driving Under Pedestrian Behavioral Uncertainty

    cs.LG 2026-05 unverdicted novelty 5.0

    Co-training an SDC and 12 pedestrians with MAPPO in a MARL setup yields 78% goal success and 14% collisions versus 35% goals and 33% for the best rule-based baseline, with jaywalking linked to 62% of collisions despit...

  13. Detecting Explanatory Insufficiency in Learned Representations: A Framework for Representational Vigilance

    cs.LG 2026-06 unverdicted novelty 4.0

    Proposes the VER framework as a diagnostic sequence for identifying explanatory insufficiency in learned representations, distinguishing it from standard errors and shifts.

  14. Position: Prioritize Identifying Structure, Not Complex Models, for Scientific Discovery

    stat.ML 2026-05 unverdicted novelty 4.0

    Mechanistic learning from ML is generically underdetermined in high-dimensional proxy regimes, with LLMs worsening the problem by collapsing many possible explanations into one fluent narrative.

  15. Multi-Agent Reinforcement Learning for Safe Autonomous Driving Under Pedestrian Behavioral Uncertainty

    cs.LG 2026-05 unverdicted novelty 4.0

    Co-training an SDC and pedestrians with MAPPO yields 78% goal success and 14% collisions versus 35%/33% for rule-based baselines, with jaywalking causing 62% of collisions and evidence of poor anticipation via speed d...

  16. Uncertainty in Physics and AI: Taxonomy, Quantification, and Validation

    stat.ML 2026-05 accept novelty 4.0

    A unified taxonomy of uncertainty in ML for physics is introduced together with validation tools such as coverage, calibration, and proper scoring rules, illustrated on regression and classification tasks.

  17. Modelling magnetic material properties with uncertainty-aware neural networks

    cond-mat.mtrl-sci 2026-06 unverdicted novelty 3.0

    Uncertainty-aware neural networks using Gaussian negative log-likelihood and dropout are applied to predict intrinsic magnetic properties and coercivity via graph neural networks in permanent magnet research.