jfc43 / informative-outlier-miningLinks
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.
☆57Updated 3 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
Sorting:
- On the Importance of Gradients for Detecting Distributional Shifts in the Wild☆56Updated 3 years ago
- Learning from Failure: Training Debiased Classifier from Biased Classifier (NeurIPS 2020)☆91Updated 4 years ago
- ☆49Updated 2 years ago
- Code for "Just Train Twice: Improving Group Robustness without Training Group Information"☆72Updated last year
- Coresets via Bilevel Optimization☆66Updated 4 years ago
- Official implementation of paper Gradient Matching for Domain Generalization☆122Updated 3 years ago
- ☆16Updated 3 years ago
- Robust Out-of-distribution Detection in Neural Networks☆73Updated 3 years ago
- This is the code for the paper Bayesian Invariant Risk Minmization of CVPR 2022.☆44Updated 2 years ago
- [NeurIPS 2020] “ Robust Pre-Training by Adversarial Contrastive Learning”, Ziyu Jiang, Tianlong Chen, Ting Chen, Zhangyang Wang☆114Updated 3 years ago
- Code for the paper "Adversarial Self-supervised Contrastive Learning" (NeurIPS 2020)☆171Updated 2 years ago
- ☆108Updated last year
- ☆23Updated 3 years ago
- Code for Environment Inference for Invariant Learning (ICML 2021 Paper)☆50Updated 4 years ago
- ☆44Updated 4 months ago
- ☆37Updated 4 years ago
- Official PyTorch implementation of the Fishr regularization for out-of-distribution generalization☆87Updated 3 years ago
- Code for NeurIPS 2021 paper "ReAct: Out-of-distribution Detection With Rectified Activations"☆53Updated 3 years ago
- PyTorch implementation of POEM (Out-of-distribution detection with posterior sampling), ICML 2022☆28Updated 2 years ago
- Pytorch SimCLR on CIFAR10 (92.85% test accuracy)☆57Updated 5 years ago
- ☆46Updated 4 years ago
- A way to achieve uniform confidence far away from the training data.☆38Updated 4 years ago
- Repo for the paper: "Agree to Disagree: Diversity through Disagreement for Better Transferability"☆36Updated 2 years ago
- A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks☆231Updated 6 years ago
- Code for Model Agnostic Sample Reweighting for Out-of-Distribution Learning☆44Updated 2 years ago
- Implementation of Contrastive Learning with Adversarial Examples☆29Updated 4 years ago
- Code for the paper Domain Adaptation with Conditional Distribution Matching and Generalized Label Shift☆38Updated 4 years ago
- Distributionally robust neural networks for group shifts☆276Updated 2 years ago
- ☆27Updated 2 years ago
- Simple data balancing baselines for worst-group-accuracy benchmarks.☆42Updated last year