HazyResearch / model-patching
Model Patching: Closing the Subgroup Performance Gap with Data Augmentation
☆42Updated 3 years ago
Related projects: ⓘ
- Code for the CVPR 2021 paper: Understanding Failures of Deep Networks via Robust Feature Extraction☆35Updated 2 years ago
- Fine-grained ImageNet annotations☆29Updated 4 years ago
- ☆40Updated last year
- Active and Sample-Efficient Model Evaluation☆24Updated 3 years ago
- Combating hidden stratification with GEORGE☆62Updated 3 years ago
- ☆37Updated 3 years ago
- Gradient Starvation: A Learning Proclivity in Neural Networks☆59Updated 3 years ago
- ☆33Updated 3 years ago
- An uncertainty-based random sampling algorithm for data augmentation☆29Updated 4 years ago
- An Empirical Study of Invariant Risk Minimization☆28Updated 4 years ago
- ☆32Updated 11 months ago
- [NeurIPS 2020] Coresets for Robust Training of Neural Networks against Noisy Labels☆33Updated 3 years ago
- DiWA: Diverse Weight Averaging for Out-of-Distribution Generalization☆27Updated last year
- ☆55Updated 4 years ago
- ☆34Updated 3 years ago
- Implementation of the models and datasets used in "An Information-theoretic Approach to Distribution Shifts"☆24Updated 2 years ago
- MODALS: Modality-agnostic Automated Data Augmentation in the Latent Space☆40Updated 3 years ago
- Code to study the generalisability of benchmark models on non-stationary EHRs.☆14Updated 5 years ago
- The official repository for "Intermediate Layers Matter in Momentum Contrastive Self Supervised Learning" paper.☆40Updated 2 years ago
- Pytorch implementation for "The Surprising Positive Knowledge Transfer in Continual 3D Object Shape Reconstruction"☆33Updated 2 years ago
- Improving Transformation Invariance in Contrastive Representation Learning☆13Updated 3 years ago
- ☆41Updated 3 years ago
- [ICLR'22] Self-supervised learning optimally robust representations for domain shift.☆23Updated 2 years ago
- Code for "Supermasks in Superposition"☆115Updated 11 months ago
- Toy datasets to evaluate algorithms for domain generalization and invariance learning.☆42Updated 2 years ago
- Reproducible code for Augmentation paper☆18Updated 5 years ago
- Simple data balancing baselines for worst-group-accuracy benchmarks.☆39Updated 10 months ago
- Code for paper "Can contrastive learning avoid shortcut solutions?" NeurIPS 2021.☆47Updated 2 years ago
- An adaptive training algorithm for residual network☆14Updated 4 years ago
- ☆19Updated 2 years ago