j-cb / GOODLinks
Provable Worst Case Guarantees for the Detection of Out-of-Distribution Data
☆13Updated 3 years ago
Alternatives and similar repositories for GOOD
Users that are interested in GOOD are comparing it to the libraries listed below
Sorting:
- ☆12Updated 7 months ago
- Do input gradients highlight discriminative features? [NeurIPS 2021] (https://arxiv.org/abs/2102.12781)☆13Updated 2 years ago
- Simple data balancing baselines for worst-group-accuracy benchmarks.☆42Updated last year
- Official repo for the paper "Make Some Noise: Reliable and Efficient Single-Step Adversarial Training" (https://arxiv.org/abs/2202.01181)☆25Updated 2 years ago
- A way to achieve uniform confidence far away from the training data.☆38Updated 4 years ago
- A modern look at the relationship between sharpness and generalization [ICML 2023]☆43Updated 2 years ago
- Post-processing for fair classification☆16Updated 2 months ago
- ☆12Updated 3 years ago
- ☆18Updated 3 years ago
- Distilling Model Failures as Directions in Latent Space☆47Updated 2 years ago
- Implementation of the models and datasets used in "An Information-theoretic Approach to Distribution Shifts"☆25Updated 3 years ago
- DiWA: Diverse Weight Averaging for Out-of-Distribution Generalization☆31Updated 2 years ago
- ☆37Updated last year
- Official code for "In Search of Robust Measures of Generalization" (NeurIPS 2020)☆28Updated 4 years ago
- Code and results accompanying our paper titled RLSbench: Domain Adaptation under Relaxed Label Shift☆35Updated 2 years ago
- ☆57Updated 3 years ago
- Improving Transformation Invariance in Contrastive Representation Learning☆13Updated 4 years ago
- ☆55Updated 5 years ago
- ☆38Updated 4 years ago
- Source code of "Hold me tight! Influence of discriminative features on deep network boundaries"☆21Updated 3 years ago
- ☆34Updated 3 months ago
- ☆36Updated 3 years ago
- ☆46Updated 2 years ago
- ☆34Updated 4 years ago
- ☆18Updated 2 years ago
- ☆109Updated 2 years ago
- Fast Axiomatic Attribution for Neural Networks (NeurIPS*2021)☆16Updated 2 years ago
- Code for "Just Train Twice: Improving Group Robustness without Training Group Information"☆72Updated last year
- LISA for ICML 2022☆51Updated 2 years ago
- Code for the paper "Data Feedback Loops: Model-driven Amplification of Dataset Biases"☆16Updated 3 years ago