rgeirhos / shortcut-perspectiveLinks
Figures & code from the paper "Shortcut Learning in Deep Neural Networks" (Nature Machine Intelligence 2020)
☆101Updated 3 years ago
Alternatives and similar repositories for shortcut-perspective
Users that are interested in shortcut-perspective are comparing it to the libraries listed below
Sorting:
- Gradient Starvation: A Learning Proclivity in Neural Networks☆61Updated 4 years ago
- ☆141Updated 5 years ago
- Information Bottlenecks for Attribution☆82Updated 2 years ago
- Code for using CDEP from the paper "Interpretations are useful: penalizing explanations to align neural networks with prior knowledge" ht…☆128Updated 4 years ago
- Code for the CVPR 2021 paper: Understanding Failures of Deep Networks via Robust Feature Extraction☆36Updated 3 years ago
- ☆34Updated 4 years ago
- Model Patching: Closing the Subgroup Performance Gap with Data Augmentation☆42Updated 4 years ago
- Code for "Supermasks in Superposition"☆124Updated 2 years ago
- Official PyTorch implementation of the Fishr regularization for out-of-distribution generalization☆88Updated 3 years ago
- Combating hidden stratification with GEORGE☆64Updated 4 years ago
- ☆46Updated 2 years ago
- Official implementation of paper Gradient Matching for Domain Generalization☆122Updated 3 years ago
- Code for the intrinsic dimensionality estimate of data representations☆84Updated 5 years ago
- Explaining Image Classifiers by Counterfactual Generation☆28Updated 3 years ago
- Implementation of Invariant Risk Minimization https://arxiv.org/abs/1907.02893☆91Updated 5 years ago
- code release for the paper "On Completeness-aware Concept-Based Explanations in Deep Neural Networks"☆53Updated 3 years ago
- ☆63Updated 5 years ago
- Winning Solution of the NeurIPS 2020 Competition on Predicting Generalization in Deep Learning☆40Updated 4 years ago
- Combine multiple MNIST digits to create datasets with 100/1000 classes for few-shot learning/meta-learning☆101Updated 4 years ago
- ☆55Updated 5 years ago
- Official Pytorch implementation of ReBias (Learning De-biased Representations with Biased Representations), ICML 2020☆174Updated last year
- Code for "Just Train Twice: Improving Group Robustness without Training Group Information"☆72Updated last year
- Original dataset release for CIFAR-10H☆83Updated 4 years ago
- ☆38Updated 4 years ago
- Simple data balancing baselines for worst-group-accuracy benchmarks.☆42Updated last year
- Using / reproducing ACD from the paper "Hierarchical interpretations for neural network predictions" 🧠 (ICLR 2019)☆129Updated 4 years ago
- Towards Automatic Concept-based Explanations☆161Updated last year
- ICLR 2021, Fair Mixup: Fairness via Interpolation☆57Updated 4 years ago
- Pre-Training Buys Better Robustness and Uncertainty Estimates (ICML 2019)☆100Updated 3 years ago
- ☆38Updated 4 years ago