jfc43 / informative-outlier-mining
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
- A way to achieve uniform confidence far away from the training data.☆37Updated 3 years ago
- On the Importance of Gradients for Detecting Distributional Shifts in the Wild☆55Updated 2 years ago
- Robust Out-of-distribution Detection in Neural Networks☆72Updated 2 years ago
- Learning from Failure: Training Debiased Classifier from Biased Classifier (NeurIPS 2020)☆90Updated 4 years ago
- ☆16Updated 2 years ago
- ☆46Updated 4 years ago
- Code for "Just Train Twice: Improving Group Robustness without Training Group Information"☆71Updated 10 months ago
- ☆108Updated last year
- Code for Environment Inference for Invariant Learning (ICML 2021 Paper)☆50Updated 3 years ago
- Official implementation of paper Gradient Matching for Domain Generalization☆119Updated 3 years ago
- Code for the paper Domain Adaptation with Conditional Distribution Matching and Generalized Label Shift☆37Updated 4 years ago
- Sinkhorn Label Allocation is a label assignment method for semi-supervised self-training algorithms. The SLA algorithm is described in fu…☆53Updated 3 years ago
- Simple data balancing baselines for worst-group-accuracy benchmarks.☆42Updated last year
- A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks☆226Updated 6 years ago
- ☆64Updated 4 years ago
- ☆48Updated 2 years ago
- Example implementation for the paper: (ICLR Oral) Learning Robust Representations by Projecting Superficial Statistics Out☆27Updated 3 years ago
- Description Code for the paper "Robust Inference via Generative Classifiers for Handling Noisy Labels".☆32Updated 5 years ago
- Code for NeurIPS 2021 paper "ReAct: Out-of-distribution Detection With Rectified Activations"☆52Updated 3 years ago
- [NeurIPS 2020] “ Robust Pre-Training by Adversarial Contrastive Learning”, Ziyu Jiang, Tianlong Chen, Ting Chen, Zhangyang Wang☆115Updated 3 years ago
- ☆22Updated 2 years ago
- Pre-Training Buys Better Robustness and Uncertainty Estimates (ICML 2019)☆100Updated 3 years ago
- "Maximum-Entropy Adversarial Data Augmentation for Improved Generalization and Robustness" (NeurIPS 2020).☆50Updated 4 years ago
- Code to replicate the key results from Exploring the Limits of Out-of-Distribution Detection (https://arxiv.org/abs/2106.03004) by Stanis…☆43Updated 3 years ago
- Official PyTorch implementation of the Fishr regularization for out-of-distribution generalization☆85Updated 2 years ago
- Coresets via Bilevel Optimization☆65Updated 4 years ago
- Repo for the paper: "Agree to Disagree: Diversity through Disagreement for Better Transferability"☆35Updated 2 years ago
- [NeurIPS'22] Official Repository for Characterizing Datapoints via Second-Split Forgetting☆15Updated last year
- The Pitfalls of Simplicity Bias in Neural Networks [NeurIPS 2020] (http://arxiv.org/abs/2006.07710v2)☆39Updated last year
- ☆28Updated 3 years ago