Gaussian belief propagation solver for noisy linear systems with real coefficients and variables.
-
Updated
Mar 17, 2019 - MATLAB
Gaussian belief propagation solver for noisy linear systems with real coefficients and variables.
[ICML2020] Normalized Loss Functions for Deep Learning with Noisy Labels
Implements the CAIRAD techique for detecting noisy values in a dataset for Weka
Program for non-planar camera calibration, mean square error, RANSAC algorithm, and testing with & without noisy data using extracted 3D world and 2D image feature points.
Implementations of various NMF algorithms on the ORL and cropped YaleB datasets.
Attentively Embracing Noise for Robust Latent Representation in BERT (COLING 2020)
Least squares and recursive least squares implementation. 2D line fit to noisy data.
Analysis of robust classification algorithms for overcoming class-dependant labelling noise: Forward, Importance Reweighting and T-revision. We demonstrate methods for estimating the transition matrix in order to obtain better classifier performance when working with noisy data.
AAAI 2021: Robustness of Accuracy Metric and its Inspirations in Learning with Noisy Labels
AAAI 2021: Beyond Class-Conditional Assumption: A Primary Attempt to Combat Instance-Dependent Label Noise
Methods for numerical differentiation of noisy data in python
Predict dense depth maps from sparse and noisy LiDAR frames guided by RGB images. (Ranked 1st place on KITTI) [2019]
SMARTboost (boosting of smooth symmetric regression trees)
The FactorGraph package provides the set of different functions to perform inference over the factor graph with continuous or discrete random variables using the belief propagation algorithm.
Dynamic Mixing For Speech Processing (mix-on-the-fly)
This implementation is based on the multi-task label cleaning network proposed by Inoue et. al. in the paper "Multi-Label Fashion Image Classification with Minimal Human Supervision"
Enhanced awesome-align for low-resource languages and noise simulation: https://arxiv.org/abs/2301.09685
Code for MentorNet: Learning Data-Driven Curriculum for Very Deep Neural Networks
Self-Supervised Learning for Outlier Detection.
Add a description, image, and links to the noisy-data topic page so that developers can more easily learn about it.
To associate your repository with the noisy-data topic, visit your repo's landing page and select "manage topics."