Success of Uncertainty-Aware Deep Models Depends on Data Manifold Geometry
Not on the map. Why?
Abstract (arXiv)
For responsible decision making in safety-critical settings, machine learning models must effectively detect and process edge-case data. Although existing works show that predictive uncertainty is useful for these tasks, it is not evident from literature which uncertainty-aware models are best suited for a given dataset. Thus, we compare six uncertainty-aware deep learning models on a set of edge-case tasks: robustness to adversarial attacks as well as out-of-distribution and adversarial detection. We find that the geometry of the data sub-manifold is an important factor in determining the success of various models. Our finding suggests an interesting direction in the study of uncertainty-aware deep learning models.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 20 of its 23 references that are in the map. First posted on arXiv 2 Aug 2022.
Builds on
20 of 23 references.
References · 20
- 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,416
- 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,888
- 2017What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?cited by 2,335
- 2016Practical Black-Box Attacks against Machine Learningcited by 893
- 2018Predictive Uncertainty Estimation via Prior Networkscited by 555
- 2019A Simple Baseline for Bayesian Uncertainty in Deep Learningcited by 555
- 2017Adversarial Examples Are Not Easily Detected: Bypassing Ten Detection Methodscited by 542
- 2016Transferability in Machine Learning: from Phenomena to Black-Box Attacks using Adversarial Samplescited by 439
- 2020Simple and Principled Uncertainty Estimation with Deterministic Deep Learning via Distance Awarenesscited by 389
- 2021The Intrinsic Dimension of Images and Its Impact on Learningcited by 307
- 2017Detecting Adversarial Samples from Artifactscited by 244
- 2018Understanding Measures of Uncertainty for Adversarial Example Detectioncited by 177
8 more
- 2021Repulsive Deep Ensembles are Bayesiancited by 103
- 2021Uncertainty Baselines: Benchmarks for Uncertainty & Robustness in Deep Learningcited by 81
- 2022Deep Ensembles Work, But Are They Necessary?cited by 63
- 2019A Systematic Comparison of Bayesian Deep Learning Robustness in Diabetic Retinopathy Taskscited by 62
- 2017Adversarial Examples, Uncertainty, and Transfer Testing Robustness in Gaussian Process Hybrid Deep Networkscited by 48
- 2020Robustness of Bayesian Neural Networks to Gradient-Based Attackscited by 48
- 2020A Comparison of Uncertainty Estimation Approaches in Deep Learning Components for Autonomous Vehicle Applicationscited by 19
- 2019Minimum Uncertainty Based Detection of Adversaries in Deep Neural Networkscited by 8
Built on by
Citing papers per year: 2025: 1.
1 paper.