HazyResearch / hidden-stratificationLinks
Combating hidden stratification with GEORGE
☆64Updated 4 years ago
Alternatives and similar repositories for hidden-stratification
Users that are interested in hidden-stratification are comparing it to the libraries listed below
Sorting:
- Model Patching: Closing the Subgroup Performance Gap with Data Augmentation☆42Updated 4 years ago
- Code for the paper "Calibrating Deep Neural Networks using Focal Loss"☆160Updated last year
- Reusable BatchBALD implementation☆79Updated last year
- Code for using CDEP from the paper "Interpretations are useful: penalizing explanations to align neural networks with prior knowledge" ht…☆128Updated 4 years ago
- Figures & code from the paper "Shortcut Learning in Deep Neural Networks" (Nature Machine Intelligence 2020)☆99Updated 3 years ago
- NumPy library for calibration metrics☆73Updated 5 months ago
- Algorithms for abstention, calibration and domain adaptation to label shift.☆37Updated 4 years ago
- Using / reproducing ACD from the paper "Hierarchical interpretations for neural network predictions" 🧠 (ICLR 2019)☆129Updated 3 years ago
- Active and Sample-Efficient Model Evaluation☆24Updated 2 months ago
- ☆112Updated 2 years ago
- The official repository for "Intermediate Layers Matter in Momentum Contrastive Self Supervised Learning" paper.☆40Updated 3 years ago
- code release for the paper "On Completeness-aware Concept-Based Explanations in Deep Neural Networks"☆53Updated 3 years ago
- Simple data balancing baselines for worst-group-accuracy benchmarks.☆42Updated last year
- Calibration library and code for the paper: Verified Uncertainty Calibration. Ananya Kumar, Percy Liang, Tengyu Ma. NeurIPS 2019 (Spotlig…☆150Updated 2 years ago
- Wasserstein Adversarial Active Learning☆29Updated 5 years ago
- An Empirical Framework for Domain Generalization In Clinical Settings☆31Updated 3 years ago
- ☆37Updated 4 years ago
- Gradient Starvation: A Learning Proclivity in Neural Networks☆61Updated 4 years ago
- Library implementing state-of-the-art Concept-based and Disentanglement Learning methods for Explainable AI