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
- Code for the CVPR 2021 paper: Understanding Failures of Deep Networks via Robust Feature Extraction☆35Updated 2 years ago
- Source code of "Hold me tight! Influence of discriminative features on deep network boundaries"☆22Updated 2 years ago
- Code for the paper "Getting a CLUE: A Method for Explaining Uncertainty Estimates"☆36Updated 6 months ago
- On the effectiveness of adversarial training against common corruptions [UAI 2022]☆30Updated 2 years ago
- Do input gradients highlight discriminative features? [NeurIPS 2021] (https://arxiv.org/abs/2102.12781)☆13Updated last year
- ☆18Updated 3 years ago
- ☆35Updated 3 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
- Diagnosing Vulnerability of Variational Auto-Encoders to Adversarial Attacks☆13Updated 2 years ago
- Code and results accompanying our paper titled RLSbench: Domain Adaptation under Relaxed Label Shift☆35Updated last year
- Implementation of the paper "Understanding anomaly detection with deep invertible networks through hierarchies of distributions and featu…☆42Updated 3 years ago
- Pytorch implementation for "The Surprising Positive Knowledge Transfer in Continual 3D Object Shape Reconstruction"☆33Updated 2 years ago
- Implementation of the models and datasets used in "An Information-theoretic Approach to Distribution Shifts"☆25Updated 3 years ago
- Self-Explaining Neural Networks☆39Updated 4 years ago
- Rethinking Bias-Variance Trade-off for Generalization of Neural Networks☆49Updated 3 years ago
- Simple data balancing baselines for worst-group-accuracy benchmarks.☆40Updated last year
- MetaQuantus is an XAI performance tool to identify reliable evaluation metrics☆30Updated 6 months 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
- Contains notebooks for the PAR tutorial at CVPR 2021.☆36Updated 3 years ago
- CIFAR-5m dataset☆39Updated 3 years ago
- Anytime Learning At Macroscale☆9Updated 2 years ago
- A regularized self-labeling approach to improve the generalization and robustness of fine-tuned models☆27Updated 2 years ago
- ☆41Updated last year
- This repository contains an official implementation of LPBNN.☆39Updated last year
- General purpose library for BNNs, and implementation of OC-BNNs in our 2020 NeurIPS paper.☆38Updated 2 years ago
- Official PyTorch implementation for our ICCV 2019 paper - Fooling Network Interpretation in Image Classification☆24Updated 4 years 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
- Python implementation for evaluating explanations presented in "On the (In)fidelity and Sensitivity for Explanations" in NeurIPS 2019 for…☆25Updated 2 years ago
- CVPR'19 experiments with (on-manifold) adversarial examples.☆44Updated 4 years ago
- Winning Solution of the NeurIPS 2020 Competition on Predicting Generalization in Deep Learning☆39Updated 3 years ago