ondrejbohdal / meta-calibration
Official PyTorch implementation of "Meta-Calibration: Learning of Model Calibration Using Differentiable Expected Calibration Error"
☆32Updated last year
Related projects ⓘ
Alternatives and complementary repositories for meta-calibration
- Official PyTorch implementation of the Fishr regularization for out-of-distribution generalization☆83Updated 2 years ago
- ☆34Updated 3 years ago
- ☆41Updated last year
- Pytorch code for "Improving Self-Supervised Learning by Characterizing Idealized Representations"☆40Updated last year
- Code and results accompanying our paper titled RLSbench: Domain Adaptation under Relaxed Label Shift☆35Updated last year
- Code for "Just Train Twice: Improving Group Robustness without Training Group Information"☆66Updated 5 months ago
- ☆30Updated 3 years ago
- A regularized self-labeling approach to improve the generalization and robustness of fine-tuned models☆27Updated 2 years ago
- LISA for ICML 2022☆47Updated last year
- Official implementation of paper Gradient Matching for Domain Generalization☆116Updated 2 years ago
- ☆35Updated 3 years ago
- ☆58Updated 2 years ago
- This repository contains the code of the distribution shift framework presented in A Fine-Grained Analysis on Distribution Shift (Wiles e…☆81Updated 2 weeks ago
- ☆58Updated last year
- Pytorch library for model calibration metrics and visualizations as well as recalibration methods. In progress!☆68Updated 6 months ago
- Repo for the paper: "Agree to Disagree: Diversity through Disagreement for Better Transferability"☆35Updated 2 years ago
- Gradient Starvation: A Learning Proclivity in Neural Networks☆60Updated 3 years ago
- Repository for the NeurIPS 2023 paper "Beyond Confidence: Reliable Models Should Also Consider Atypicality"☆12Updated 6 months ago
- ☆109Updated 2 years ago
- ☆18Updated 3 years ago
- An Empirical Study of Invariant Risk Minimization☆28Updated 4 years ago
- Simple data balancing baselines for worst-group-accuracy benchmarks.☆40Updated last year
- Code of our method MbLS (Margin-based Label Smoothing) for network calibration. To Appear at CVPR 2022. Paper : https://arxiv.org/abs/211…☆48Updated last year
- This repository is the official implementation of Unleashing the Power of Contrastive Self-Supervised Visual Models via Contrast-Regulari…☆21Updated last year
- Learning Representations that Support Robust Transfer of Predictors☆20Updated 3 years ago
- Evaluating Robustness of Predictive Uncertainty Estimation: Are Dirichlet-based Models Reliable ? (ICML 2021)☆27Updated last year
- ☆38Updated this week
- Pytorch implementation for "The Surprising Positive Knowledge Transfer in Continual 3D Object Shape Reconstruction"☆33Updated 2 years ago
- DiWA: Diverse Weight Averaging for Out-of-Distribution Generalization☆28Updated last year
- Code for "SAM as an Optimal Relaxation of Bayes", ICLR 2023.☆22Updated last year