frederick0329 / TracIn
Implementation of Estimating Training Data Influence by Tracing Gradient Descent (NeurIPS 2020)
☆227Updated 3 years ago
Alternatives and similar repositories for TracIn:
Users that are interested in TracIn are comparing it to the libraries listed below
- ☆468Updated 7 months ago
- ☆201Updated 2 years ago
- NumPy library for calibration metrics☆69Updated 2 weeks ago
- A machine learning benchmark of in-the-wild distribution shifts, with data loaders, evaluators, and default models.☆558Updated last year
- Using / reproducing ACD from the paper "Hierarchical interpretations for neural network predictions" 🧠 (ICLR 2019)☆128Updated 3 years ago
- Code for the paper "Calibrating Deep Neural Networks using Focal Loss"☆160Updated last year
- Estimating Example Difficulty using Variance of Gradients☆62Updated 2 years ago
- REVISE: A Tool for Measuring and Mitigating Bias in Visual Datasets --- https://arxiv.org/abs/2004.07999☆110Updated 2 years ago
- ImageNet Testbed, associated with the paper "Measuring Robustness to Natural Distribution Shifts in Image Classification."☆118Updated last year
- ☆156Updated 2 years ago
- Pitfalls of In-Domain Uncertainty Estimation and Ensembling in Deep Learning, ICLR 2020☆235Updated 2 years ago
- Original dataset release for CIFAR-10H☆82Updated 4 years ago
- Reduce end to end training time from days to hours (or hours to minutes), and energy requirements/costs by an order of magnitude using co…☆327Updated last year
- Calibration library and code for the paper: Verified Uncertainty Calibration. Ananya Kumar, Percy Liang, Tengyu Ma. NeurIPS 2019 (Spotlig…☆145Updated 2 years ago
- Calibration of Convolutional Neural Networks☆160Updated last year
- Official repository for CMU Machine Learning Department's 10732: Robustness and Adaptivity in Shifting Environments☆73Updated 2 years ago
- ☆51Updated 4 years ago
- An essential implementation of BYOL in PyTorch + PyTorch Lightning☆51Updated 3 years ago
- Understanding Training Dynamics of Deep ReLU Networks☆284Updated last month
- ☆62Updated 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 …☆354Updated 7 months ago
- Wrapper for a PyTorch classifier which allows it to output prediction sets. The sets are theoretically guaranteed to contain the true cla…☆237Updated 2 years ago
- ☆140Updated 4 years ago
- A new test set for ImageNet☆247Updated last year
- Mode Connectivity and Fast Geometric Ensembles in PyTorch☆268Updated 2 years ago
- Code for using CDEP from the paper "Interpretations are useful: penalizing explanations to align neural networks with prior knowledge" ht…☆127Updated 3 years ago
- ☆95Updated 2 years ago
- Benchmark for Lifelong learning research☆119Updated 3 years ago
- Optimal Transport Dataset Distance☆162Updated 2 years ago
- This repository contains the code of the distribution shift framework presented in A Fine-Grained Analysis on Distribution Shift (Wiles e…☆82Updated this week