harshays / simplicitybiaspitfallsView external linksLinks
The Pitfalls of Simplicity Bias in Neural Networks [NeurIPS 2020] (http://arxiv.org/abs/2006.07710v2)
☆42Jan 21, 2024Updated 2 years ago
Alternatives and similar repositories for simplicitybiaspitfalls
Users that are interested in simplicitybiaspitfalls are comparing it to the libraries listed below
Sorting:
- Repo for the paper: "Agree to Disagree: Diversity through Disagreement for Better Transferability"☆36Oct 25, 2022Updated 3 years ago
- Demonstrates failures of bias mitigation methods under varying types/levels of biases (WACV 2021)☆26Mar 31, 2024Updated last year
- Code for the paper "Evading Black-box Classifiers Without Breaking Eggs" [SaTML 2024]☆21Apr 15, 2024Updated last year
- Learning from Failure: Training Debiased Classifier from Biased Classifier (NeurIPS 2020)☆94Oct 22, 2020Updated 5 years ago
- Distributionally robust neural networks for group shifts☆293Jan 3, 2023Updated 3 years ago
- Codebase for Mechanistic Mode Connectivity☆13Jul 14, 2023Updated 2 years ago
- ☆111Sep 20, 2023Updated 2 years ago
- ☆13Mar 22, 2023Updated 2 years ago
- An Investigation of Why Overparameterization Exacerbates Spurious Correlations☆30Jul 12, 2020Updated 5 years ago
- Training vision models with full-batch gradient descent and regularization☆39Feb 14, 2023Updated 2 years ago
- ☆34Mar 13, 2021Updated 4 years ago
- Do input gradients highlight discriminative features? [NeurIPS 2021] (https://arxiv.org/abs/2102.12781)☆13Jan 10, 2023Updated 3 years ago
- ☆16Jul 20, 2023Updated 2 years ago
- ☆36Sep 23, 2022Updated 3 years ago
- Gradient Starvation: A Learning Proclivity in Neural Networks☆61Jan 10, 2021Updated 5 years ago
- Source code for "Neural Anisotropy Directions"☆16Nov 17, 2020Updated 5 years ago
- ☆143Oct 2, 2020Updated 5 years ago
- Simple data balancing baselines for worst-group-accuracy benchmarks.☆43Oct 24, 2023Updated 2 years ago
- Implementation of paper "Do Wide and Deep Networks Learn the Same Things?"☆16Mar 15, 2022Updated 3 years ago
- Code for ICML 2019 paper "Simple Black-box Adversarial Attacks"☆200Mar 27, 2023Updated 2 years ago
- MIT MIC Reading Groups☆16Apr 13, 2021Updated 4 years ago
- SurFree: a fast surrogate-free black-box attack☆44Jun 27, 2024Updated last year
- Dataset Interfaces: Diagnosing Model Failures Using Controllable Counterfactual Generation☆45Feb 27, 2023Updated 2 years ago
- Code for "Just Train Twice: Improving Group Robustness without Training Group Information"☆73May 18, 2024Updated last year
- "Predict, then Interpolate: A Simple Algorithm to Learn Stable Classifiers" ICML 2021☆18Jun 1, 2021Updated 4 years ago
- Source code of "What can linearized neural networks actually say about generalization?☆20Oct 21, 2021Updated 4 years ago
- [CVPR 2024] This repository includes the official implementation our paper "Revisiting Adversarial Training at Scale"☆20Apr 21, 2024Updated last year
- Code relative to "Adversarial robustness against multiple and single $l_p$-threat models via quick fine-tuning of robust classifiers"☆19Nov 30, 2022Updated 3 years ago
- ☆23Jan 25, 2024Updated 2 years ago
- ☆21Oct 23, 2024Updated last year
- ☆23Apr 5, 2023Updated 2 years ago
- ☆21Apr 10, 2023Updated 2 years ago
- SGD with large step sizes learns sparse features [ICML 2023]☆33Apr 24, 2023Updated 2 years ago
- [ICML'20] Multi Steepest Descent (MSD) for robustness against the union of multiple perturbation models.☆25Jul 25, 2024Updated last year
- ☆32Aug 22, 2020Updated 5 years ago
- A machine learning benchmark of in-the-wild distribution shifts, with data loaders, evaluators, and default models.☆592Jan 26, 2024Updated 2 years ago
- ModelDiff: A Framework for Comparing Learning Algorithms☆58Aug 15, 2023Updated 2 years ago
- Code for Environment Inference for Invariant Learning (ICML 2021 Paper)☆51Jun 10, 2021Updated 4 years ago
- ☆56Aug 14, 2020Updated 5 years ago