MadryLab / failure-directionsLinks
Distilling Model Failures as Directions in Latent Space
☆47Updated 2 years ago
Alternatives and similar repositories for failure-directions
Users that are interested in failure-directions are comparing it to the libraries listed below
Sorting:
- A modern look at the relationship between sharpness and generalization [ICML 2023]☆43Updated 2 years ago
- Code for the ICLR 2022 paper. Salient Imagenet: How to discover spurious features in deep learning?☆40Updated 3 years ago
- ☆46Updated 2 years ago
- Spurious Features Everywhere - Large-Scale Detection of Harmful Spurious Features in ImageNet☆32Updated 2 years ago
- ModelDiff: A Framework for Comparing Learning Algorithms☆59Updated 2 years ago
- ☆108Updated 2 years ago
- Towards Understanding Sharpness-Aware Minimization [ICML 2022]☆35Updated 3 years ago
- [NeurIPS 2021] A Geometric Analysis of Neural Collapse with Unconstrained Features☆58Updated 3 years ago
- ☆18Updated 2 years ago
- ☆55Updated 5 years ago
- Post-processing for fair classification☆16Updated 2 months ago
- An Investigation of Why Overparameterization Exacerbates Spurious Correlations☆30Updated 5 years ago
- [ICLR'22] Self-supervised learning optimally robust representations for domain shift.☆24Updated 3 years ago
- Simple data balancing baselines for worst-group-accuracy benchmarks.☆42Updated last year
- ☆38Updated 4 years ago
- ☆34Updated last year
- Dataset Interfaces: Diagnosing Model Failures Using Controllable Counterfactual Generation☆45Updated 2 years ago
- Code for "Just Train Twice: Improving Group Robustness without Training Group Information"☆72Updated last year
- Do input gradients highlight discriminative features? [NeurIPS 2021] (https://arxiv.org/abs/2102.12781)☆13Updated 2 years ago
- Repo for the paper: "Agree to Disagree: Diversity through Disagreement for Better Transferability"☆36Updated 2 years ago
- Data for "Datamodels: Predicting Predictions with Training Data"☆97Updated 2 years ago
- ☆31Updated last year
- Code for the CVPR 2021 paper: Understanding Failures of Deep Networks via Robust Feature Extraction☆36Updated 3 years ago
- Code relative to "Adversarial robustness against multiple and single $l_p$-threat models via quick fine-tuning of robust classifiers"☆19Updated 2 years ago
- LISA for ICML 2022☆51Updated 2 years ago
- Understanding Rare Spurious Correlations in Neural Network☆12Updated 3 years ago
- Official code repository for Correct-N-Contrast☆22Updated 3 years ago
- ☆40Updated 2 years ago
- Code and results accompanying our paper titled RLSbench: Domain Adaptation under Relaxed Label Shift☆35Updated 2 years ago
- ☆27Updated last year