Stars
Python package for evaluating model calibration in classification
The official code for our TIP paper 'LayerCAM: Exploring Hierarchical Class Activation Maps for Localization'
Quantus is an eXplainable AI toolkit for responsible evaluation of neural network explanations
NoiseGrad (and its extension NoiseGrad++) is a method to enhance explanations of artificial neural networks by adding noise to model weights
Code for Deep Variational Implicit Processes (DVIP - ICLR 2023)
Code for "Functional variational Bayesian neural networks" (https://arxiv.org/abs/1903.05779)
Pytorch implementations of Bayes By Backprop, MC Dropout, SGLD, the Local Reparametrization Trick, KF-Laplace, SG-HMC and 8000 more
Reproduction for the paper : Weight uncertainty in neural networks
Bayesianize: A Bayesian neural network wrapper in pytorch
Uncertainty quantification using Bayesian neural networks in classification (MIDL 2018, CSDA)
A simple and extensible library to create Bayesian Neural Network layers on PyTorch.
LSTM-RNN Tutorial with LSTM and RNN Tutorial with Demo with Demo Projects such as Stock/Bitcoin Time Series Prediction, Sentiment Analysis, Music Generation using Keras-Tensorflow
RNN based Time-series Anomaly detector model implemented in Pytorch.
Bayesian Convolutional Neural Network with Variational Inference based on Bayes by Backprop in PyTorch.
Open-source framework for uncertainty and deep learning models in PyTorch 🌱
A methodology for generating a novel uncertainty map that complements an occupancy map allowing quantification of measurements uncertainty using a signed relative entropy. A new concept of frontier…
This repository provides the code used to implement the framework to provide deep learning models with total uncertainty estimates as described in "A General Framework for Uncertainty Estimation in…
Uncertainty Toolbox: a Python toolbox for predictive uncertainty quantification, calibration, metrics, and visualization
High-quality implementations of standard and SOTA methods on a variety of tasks.
Uncertainty-aware Semantic Segmentation of LiDAR Point Clouds for Autonomous Driving
OpenMMLab optical flow toolbox and benchmark
Code paper Uncertainty Reduction for Uncertainty Reduction for Model Adaptation in Semantic Segmentation at CVPR 2021
noisy labels; missing labels; semi-supervised learning; entropy; uncertainty; robustness and generalisation.
the code for paper "Energy-Based Open-World Uncertainty Modeling for Confidence Calibration"
Removing the spatial aliasing in the seismic data using Deep Learning Super-resolution
Deep-learning inversion: A next-generation seismic velocity model building method