We propose a theoretically motivated method, Adversarial Training with informative Outlier Mining (ATOM), which improves the robustness of OOD detection to various types of adversarial OOD inputs and establishes state-of-the-art performance.
☆57Feb 17, 2022Updated 4 years ago
Alternatives and similar repositories for informative-outlier-mining
Users that are interested in informative-outlier-mining are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- PyTorch implementation of POEM (Out-of-distribution detection with posterior sampling), ICML 2022☆28May 6, 2023Updated 3 years ago
- ☆26Mar 17, 2023Updated 3 years ago
- ☆47Dec 20, 2020Updated 5 years ago
- ☆16May 25, 2022Updated 4 years ago
- ☆439Aug 28, 2021Updated 4 years ago
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- Robust Out-of-distribution Detection in Neural Networks☆73Apr 12, 2022Updated 4 years ago
- ☆23Jun 15, 2022Updated 4 years ago
- [NeurIPS 2023] "Diversified Outlier Exposure for Out-of-Distribution Detection via Informative Extrapolation"☆11Oct 6, 2023Updated 2 years ago
- Code for CVPR2021 paper: MOOD: Multi-level Out-of-distribution Detection☆38Sep 4, 2023Updated 2 years ago
- Reproducing experimental results of OOD-by-MCD [Yu and Aizawa et al. ICCV 2019]☆30Dec 8, 2019Updated 6 years ago
- [ICML 2023] "Unleashing Mask: Explore the Intrinsic Out-of-Distribution Detection Capability"☆18Jul 7, 2023Updated 3 years ago
- Propose a principled and practically effective framework for unsupervised accuracy estimation and error detection tasks with theoretical …☆16Feb 17, 2022Updated 4 years ago
- Official code for ICML 2022: Mitigating Neural Network Overconfidence with Logit Normalization