HazyResearch / hidden-stratification
Combating hidden stratification with GEORGE
☆62Updated 3 years ago
Related projects: ⓘ
- The official repository for "Intermediate Layers Matter in Momentum Contrastive Self Supervised Learning" paper.☆40Updated 2 years ago
- Model Patching: Closing the Subgroup Performance Gap with Data Augmentation☆42Updated 3 years ago
- Pytorch library for model calibration metrics and visualizations as well as recalibration methods. In progress!☆65Updated 4 months ago
- ☆33Updated 3 years ago
- Active and Sample-Efficient Model Evaluation☆24Updated 3 years ago
- Algorithms for abstention, calibration and domain adaptation to label shift.☆36Updated 3 years ago
- Reusable BatchBALD implementation☆74Updated 6 months ago
- Figures & code from the paper "Shortcut Learning in Deep Neural Networks" (Nature Machine Intelligence 2020)☆94Updated 2 years ago
- Code to accompany the paper 'Improving model calibration with accuracy versus uncertainty optimization'.☆51Updated last year
- Wasserstein Adversarial Active Learning☆28Updated 4 years ago
- Code for the paper "Calibrating Deep Neural Networks using Focal Loss"☆149Updated 8 months ago
- ☆40Updated last year
- Code for the CVPR 2021 paper: Understanding Failures of Deep Networks via Robust Feature Extraction☆35Updated 2 years ago
- Gradient Starvation: A Learning Proclivity in Neural Networks☆59Updated 3 years ago
- Simple data balancing baselines for worst-group-accuracy benchmarks.☆39Updated 10 months ago
- ☆46Updated 3 years ago
- Code accompanying paper: Meta-Learning to Improve Pre-Training☆36Updated 2 years ago
- Pytorch code for "Improving Self-Supervised Learning by Characterizing Idealized Representations"☆40Updated last year
- Code for Active Learning at The ImageNet Scale. This repository implements many popular active learning algorithms and allows training wi…☆53Updated 2 years ago
- An Empirical Framework for Domain Generalization In Clinical Settings☆27Updated 2 years ago
- ☆46Updated 3 years ago
- Library implementing state-of-the-art Concept-based and Disentanglement Learning methods for Explainable AI☆52Updated 2 years ago
- ☆33Updated 3 years ago
- ☆16Updated 4 years ago
- This repository contains the code of the distribution shift framework presented in A Fine-Grained Analysis on Distribution Shift (Wiles e…☆82Updated last month
- Code implementation of our ICLR'21 paper "Calibration of Neural Networks using Splines"☆21Updated last year
- Model-agnostic posthoc calibration without distributional assumptions☆42Updated 11 months ago
- Code for "Just Train Twice: Improving Group Robustness without Training Group Information"☆66Updated 4 months ago
- Estimating Example Difficulty using Variance of Gradients☆60Updated last year
- ☆26Updated last month