mlsanityData to 7 Oct 2026

Introspective Robot Perception using Smoothed Predictions from Bayesian Neural Networks

arXiv 2109.12869 ↗First posted 27 Sep 2021cs.RO cs.AIcited by 5

Not on the map. Why?

Abstract (arXiv)

This work focuses on improving uncertainty estimation in the field of object classification from RGB images and demonstrates its benefits in two robotic applications. We employ a (BNN), and evaluate two practical inference techniques to obtain better uncertainty estimates, namely Concrete Dropout (CDP) and Kronecker-factored Laplace Approximation (LAP). We show a performance increase using more reliable uncertainty estimates as unary potentials within a Conditional Random Field (CRF), which is able to incorporate contextual information as well. Furthermore, the obtained uncertainties are exploited to achieve domain adaptation in a semi-supervised manner, which requires less manual efforts in annotating data. We evaluate our approach on two public benchmark datasets that are relevant for robot perception tasks.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 25 of its 43 references that are in the map. First posted on arXiv 27 Sep 2021.

Builds on

25 of 43 references.

References · 25

  1. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  2. 2017On Calibration of Modern Neural Networkscited by 4,860
  3. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,416
  4. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,888
  5. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,362
  6. 2016The Concrete Distribution: A Continuous Relaxation of Discrete Random Variablescited by 1,135
  7. 2016Adversarial Machine Learning at Scalecited by 934
  8. 2017Deep Bayesian Active Learning with Image Datacited by 812
  9. 2015Optimizing Neural Networks with Kronecker-factored Approximate Curvaturecited by 776
  10. 2016Deep Exploration via Bootstrapped DQNcited by 518
  11. 2019Revisiting Self-Supervised Visual Representation Learningcited by 250
  12. 2017Concrete Dropoutcited by 227
13 more
  1. 2017T-LESS: An RGB-D Dataset for 6D Pose Estimation of Texture-less Objectscited by 210
  2. 2017Cost-Effective Active Learning for Deep Image Classificationcited by 165
  3. 2017Multiplicative Normalizing Flows for Variational Bayesian Neural Networkscited by 157
  4. 2014Joint Training of a Convolutional Network and a Graphical Model for Human Pose Estimationcited by 129
  5. 2016Composing graphical models with neural networks for structured representations and fast inferencecited by 113
  6. 2014Deep Convolutional Neural Fields for Depth Estimation from a Single Imagecited by 106
  7. 2016Structured and Efficient Variational Deep Learning with Matrix Gaussian Posteriorscited by 82
  8. 2019Self-supervised Domain Adaptation for Computer Vision Taskscited by 58
  9. 2015Bayesian Dark Knowledgecited by 45
  10. 2018Adversarial Distillation of Bayesian Neural Network Posteriorscited by 27
  11. 2017Active Self-Paced Learning for Cost-Effective and Progressive Face Identificationcited by 19
  12. 2015CRF Learning with CNN Features for Image Segmentationcited by 6
  13. 2016A Survey on Bayesian Deep Learningcited by 2

Built on by

Cited by year

Citing papers per year: 2023: 3; 2024: 2.

5 papers.

  1. 2024Evaluating Uncertainty-based Failure Detection for Closed-Loop LLM Plannerscited by 15
  2. 2023Topology-Matching Normalizing Flows for Out-of-Distribution Detection in Robot Learningcited by 7
  3. 2024FFHFlow: Diverse and Uncertainty-Aware Dexterous Grasp Generation via Flow Variational Inferencecited by 3
  4. 2023Efficient and Feasible Robotic Assembly Sequence Planning via Graph Representation Learningcited by 2
  5. 2023Density-based Feasibility Learning with Normalizing Flows for Introspective Robotic Assemblycited by 2