understandable-machine-intelligence-lab / NoiseGrad
NoiseGrad (and its extension NoiseGrad++) is a method to enhance explanations of artificial neural networks by adding noise to model weights
☆21Updated last year
Related projects ⓘ
Alternatives and complementary repositories for NoiseGrad
- Active and Sample-Efficient Model Evaluation☆24Updated 3 years ago
- B-LRP is the repository for the paper How Much Can I Trust You? — Quantifying Uncertainties in Explaining Neural Networks☆18Updated 2 years ago
- Simple data balancing baselines for worst-group-accuracy benchmarks.☆40Updated last year
- Code for the CVPR 2021 paper: Understanding Failures of Deep Networks via Robust Feature Extraction☆35Updated 2 years ago
- MetaQuantus is an XAI performance tool to identify reliable evaluation metrics☆30Updated 7 months ago
- Python implementation for evaluating explanations presented in "On the (In)fidelity and Sensitivity for Explanations" in NeurIPS 2019 for…☆25Updated 2 years ago
- Diagnosing Vulnerability of Variational Auto-Encoders to Adversarial Attacks☆13Updated 2 years ago
- ☆18Updated 3 years ago
- Implementation of the models and datasets used in "An Information-theoretic Approach to Distribution Shifts"☆25Updated 3 years ago
- PyTorch reimplementation of computing Shapley values via Truncated Monte Carlo sampling from "What is your data worth? Equitable Valuatio…☆25Updated 2 years ago
- 👋 Code for the paper: "Look at the Variance! Efficient Black-box Explanations with Sobol-based Sensitivity Analysis" (NeurIPS 2021)☆27Updated 2 years ago
- Do input gradients highlight discriminative features? [NeurIPS 2021] (https://arxiv.org/abs/2102.12781)☆13Updated last year
- ☆41Updated last year
- A pytorch implemention of the Explainable AI work 'Contrastive layerwise relevance propagation (CLRP)'☆17Updated 2 years ago
- Influence Estimation for Gradient-Boosted Decision Trees☆25Updated 5 months ago
- Official repo for the paper "Make Some Noise: Reliable and Efficient Single-Step Adversarial Training" (https://arxiv.org/abs/2202.01181)☆25Updated 2 years ago
- Experiments on meta-learning algorithms to solve few-shot domain adaptation☆10Updated 3 years ago
- A regularized self-labeling approach to improve the generalization and robustness of fine-tuned models☆27Updated 2 years ago
- Fast Axiomatic Attribution for Neural Networks (NeurIPS*2021)☆15Updated last year
- A way to achieve uniform confidence far away from the training data.☆36Updated 3 years ago
- Source code of "Hold me tight! Influence of discriminative features on deep network boundaries"☆22Updated 2 years ago
- ☆24Updated 2 years ago
- This repository provides a PyTorch implementation of "Fooling Neural Network Interpretations via Adversarial Model Manipulation". Our pap…☆22Updated 3 years ago
- ☆35Updated 3 years ago
- Code to accompany the paper Radial Bayesian Neural Networks: Beyond Discrete Support In Large-Scale Bayesian Deep Learning☆33Updated 4 years ago
- code release for the paper "On Completeness-aware Concept-Based Explanations in Deep Neural Networks"☆51Updated 2 years ago
- Code for CVPR2021 paper: MOOD: Multi-level Out-of-distribution Detection☆38Updated last year
- Code for Fong and Vedaldi 2017, "Interpretable Explanations of Black Boxes by Meaningful Perturbation"☆30Updated 5 years ago
- Self-Explaining Neural Networks☆39Updated 4 years ago
- ☆10Updated 3 years ago