Picture for Julian Bitterwolf

Julian Bitterwolf

In or Out? Fixing ImageNet Out-of-Distribution Detection Evaluation

Add code
Jun 01, 2023
Viaarxiv icon

Breaking Down Out-of-Distribution Detection: Many Methods Based on OOD Training Data Estimate a Combination of the Same Core Quantities

Add code
Jun 20, 2022
Figure 1 for Breaking Down Out-of-Distribution Detection: Many Methods Based on OOD Training Data Estimate a Combination of the Same Core Quantities
Figure 2 for Breaking Down Out-of-Distribution Detection: Many Methods Based on OOD Training Data Estimate a Combination of the Same Core Quantities
Figure 3 for Breaking Down Out-of-Distribution Detection: Many Methods Based on OOD Training Data Estimate a Combination of the Same Core Quantities
Figure 4 for Breaking Down Out-of-Distribution Detection: Many Methods Based on OOD Training Data Estimate a Combination of the Same Core Quantities
Viaarxiv icon

Provably Robust Detection of Out-of-distribution Data (almost) for free

Add code
Jun 08, 2021
Figure 1 for Provably Robust Detection of Out-of-distribution Data (almost) for free
Figure 2 for Provably Robust Detection of Out-of-distribution Data (almost) for free
Figure 3 for Provably Robust Detection of Out-of-distribution Data (almost) for free
Figure 4 for Provably Robust Detection of Out-of-distribution Data (almost) for free
Viaarxiv icon

Provable Worst Case Guarantees for the Detection of Out-of-Distribution Data

Add code
Jul 16, 2020
Figure 1 for Provable Worst Case Guarantees for the Detection of Out-of-Distribution Data
Figure 2 for Provable Worst Case Guarantees for the Detection of Out-of-Distribution Data
Figure 3 for Provable Worst Case Guarantees for the Detection of Out-of-Distribution Data
Figure 4 for Provable Worst Case Guarantees for the Detection of Out-of-Distribution Data
Viaarxiv icon

Increasing the robustness of DNNs against image corruptions by playing the Game of Noise

Add code
Feb 26, 2020
Figure 1 for Increasing the robustness of DNNs against image corruptions by playing the Game of Noise
Figure 2 for Increasing the robustness of DNNs against image corruptions by playing the Game of Noise
Figure 3 for Increasing the robustness of DNNs against image corruptions by playing the Game of Noise
Figure 4 for Increasing the robustness of DNNs against image corruptions by playing the Game of Noise
Viaarxiv icon

Why ReLU networks yield high-confidence predictions far away from the training data and how to mitigate the problem

Add code
Dec 13, 2018
Figure 1 for Why ReLU networks yield high-confidence predictions far away from the training data and how to mitigate the problem
Figure 2 for Why ReLU networks yield high-confidence predictions far away from the training data and how to mitigate the problem
Figure 3 for Why ReLU networks yield high-confidence predictions far away from the training data and how to mitigate the problem
Figure 4 for Why ReLU networks yield high-confidence predictions far away from the training data and how to mitigate the problem
Viaarxiv icon