facebookresearch / BalancingGroups
Simple data balancing baselines for worst-group-accuracy benchmarks.
☆39Updated 10 months ago
Related projects: ⓘ
- Code for "Just Train Twice: Improving Group Robustness without Training Group Information"☆66Updated 4 months ago
- ☆34Updated 3 years ago
- ☆55Updated 4 years ago
- Toy datasets to evaluate algorithms for domain generalization and invariance learning.☆42Updated 2 years ago
- A modern look at the relationship between sharpness and generalization [ICML 2023]☆42Updated last year
- ☆102Updated 11 months ago
- ☆40Updated last year
- An Investigation of Why Overparameterization Exacerbates Spurious Correlations☆30Updated 4 years ago
- ☆65Updated 3 years ago
- ☆33Updated 3 years ago
- Gradient Starvation: A Learning Proclivity in Neural Networks☆59Updated 3 years ago
- Do input gradients highlight discriminative features? [NeurIPS 2021] (https://arxiv.org/abs/2102.12781)☆13Updated last year
- Computing various measures and generalization bounds on convolutional and fully connected networks☆33Updated 5 years ago
- The Pitfalls of Simplicity Bias in Neural Networks [NeurIPS 2020] (http://arxiv.org/abs/2006.07710v2)☆39Updated 7 months ago
- A way to achieve uniform confidence far away from the training data.☆36Updated 3 years ago
- Towards Understanding Sharpness-Aware Minimization [ICML 2022]☆34Updated 2 years ago
- ☆31Updated 7 months ago
- ☆29Updated 2 years ago
- Code to implement the AND-mask and geometric mean to do gradient based optimization, from the paper "Learning explanations that are hard …☆39Updated 3 years ago
- Invariant-feature Subspace Recovery (ISR)☆22Updated last year
- Code for the ICLR 2022 paper. Salient Imagenet: How to discover spurious features in deep learning?☆35Updated 2 years ago
- [ICLR'22] Self-supervised learning optimally robust representations for domain shift.☆23Updated 2 years ago
- ☆32Updated 11 months ago
- Distilling Model Failures as Directions in Latent Space☆45Updated last year
- Code for Environment Inference for Invariant Learning (ICML 2021 Paper)☆48Updated 3 years ago
- Code accompanying paper: Meta-Learning to Improve Pre-Training☆36Updated 2 years ago
- Contains code for the NeurIPS 2020 paper by Pan et al., "Continual Deep Learning by FunctionalRegularisation of Memorable Past"☆43Updated 3 years ago
- Official code for "In Search of Robust Measures of Generalization" (NeurIPS 2020)☆28Updated 3 years ago
- Source code of "What can linearized neural networks actually say about generalization?☆17Updated 2 years ago
- Official implementation of paper Gradient Matching for Domain Generalization☆116Updated 2 years ago