torrvision / focal_calibrationView external linksLinks
Code for the paper "Calibrating Deep Neural Networks using Focal Loss"
☆161Jan 10, 2024Updated 2 years ago
Alternatives and similar repositories for focal_calibration
Users that are interested in focal_calibration are comparing it to the libraries listed below
Sorting:
- Model-agnostic posthoc calibration without distributional assumptions☆42Oct 20, 2023Updated 2 years ago
- A simple way to calibrate your neural network.☆1,169Jul 26, 2025Updated 6 months ago
- Calibration of Convolutional Neural Networks☆171Apr 19, 2023Updated 2 years ago
- ☆15Nov 19, 2021Updated 4 years ago
- ☆19Jun 5, 2018Updated 7 years ago
- [CVPR 2022] Official code for the paper: "A Stitch in Time Saves Nine: A Train-Time Regularizing Loss for Improved Neural Network Calibra…☆33Nov 9, 2022Updated 3 years ago
- The net:cal calibration framework is a Python 3 library for measuring and mitigating miscalibration of uncertainty estimates, e.g., by a …☆372Jan 14, 2026Updated last month
- ☆429Aug 28, 2021Updated 4 years ago
- Code implementation of our ICLR'21 paper "Calibration of Neural Networks using Splines"☆22Mar 31, 2023Updated 2 years ago
- Code for "Dual Focal Loss for Calibration" (ICML 2023)☆32Apr 21, 2025Updated 9 months ago
- An easy-to-use interface for measuring uncertainty and robustness.☆15Jan 21, 2021Updated 5 years ago
- Non-Parametric Calibration for Classification (AISTATS 2020)☆19Feb 3, 2022Updated 4 years ago
- Simple data balancing baselines for worst-group-accuracy benchmarks.☆43Oct 24, 2023Updated 2 years ago
- ☆12Sep 11, 2022Updated 3 years ago
- NumPy library for calibration metrics☆76Jan 13, 2026Updated last month
- High-quality implementations of standard and SOTA methods on a variety of tasks.☆1,566Feb 2, 2026Updated last week
- [NeurIPS 2023] Towards Free Data Selection with General-Purpose Models☆41Mar 14, 2025Updated 11 months ago
- Implementation of the spotlight: a method for discovering systematic errors in deep learning models☆11Oct 5, 2021Updated 4 years ago
- Reliability diagrams visualize whether a classifier model needs calibration☆165Feb 11, 2022Updated 4 years ago
- Codebase for "A Consistent and Differentiable Lp Canonical Calibration Error Estimator", published at NeurIPS 2022.☆15Mar 18, 2024Updated last year
- ☆34May 30, 2025Updated 8 months ago
- PyTorch implementation of our ECCV 2022 paper "Rethinking Confidence Calibration for Failure Prediction"☆26Jun 10, 2023Updated 2 years ago
- Codebase for Learning Invariances in Neural Networks☆96Oct 7, 2022Updated 3 years ago
- Code and results accompanying our paper titled Leveraging Unlabeled Data to Predict Out-of-Distribution Performance at ICLR 2022☆10Dec 8, 2022Updated 3 years ago
- ☆12Sep 26, 2019Updated 6 years ago
- Improving Calibration for Long-Tailed Recognition (CVPR2021)☆153Nov 10, 2021Updated 4 years ago
- Understanding Rare Spurious Correlations in Neural Network☆12Jun 5, 2022Updated 3 years ago
- code for model-targeted poisoning☆12Oct 3, 2023Updated 2 years ago
- ☆32May 24, 2021Updated 4 years ago
- Learning Representations that Support Robust Transfer of Predictors☆20Nov 7, 2021Updated 4 years ago
- Visualizing ImageNet Classes Hierarchical Structure.☆15Apr 8, 2018Updated 7 years ago
- ☆18May 25, 2022Updated 3 years ago
- Official repository for CVPR2023 publication, GEN: Pushing the Limits of Softmax-Based Out-of-Distribution Detection☆19Sep 25, 2024Updated last year
- ImageNet Testbed, associated with the paper "Measuring Robustness to Natural Distribution Shifts in Image Classification."☆119Aug 5, 2023Updated 2 years ago
- ☆15Jul 4, 2023Updated 2 years ago
- Wrapper for a PyTorch classifier which allows it to output prediction sets. The sets are theoretically guaranteed to contain the true cla…☆255Jan 23, 2023Updated 3 years ago
- A simple algorithm to identify and correct for label shift.☆21Feb 4, 2018Updated 8 years ago
- IPython notebook with synthetic experiments for AFLite, based on the ICML 2020 paper, "Adversarial Filters of Dataset Biases".☆16Aug 14, 2020Updated 5 years ago
- Robust fine-tuning of zero-shot models☆760Apr 29, 2022Updated 3 years ago