A curated list of resources for Learning with Noisy Labels
-
Updated
May 3, 2024
A curated list of resources for Learning with Noisy Labels
Empowering Scientific Research with AI Assistance! Open Source Code for Data-Driven Dimensional Analysis.
A curated (most recent) list of resources for Learning with Noisy Labels
SMARTboost (boosting of smooth symmetric regression trees)
Kalman Filters are used for state estimation in control systems. This repository includes an implementation of the algorithm in Python and also a Jupyter Notebook for testing in real data for altitude estimation of a quadrotor
A collection of algorithms for detecting and handling label noise
All the material (code, dataset, results) of our Benchmark of Nested NER approaches accepted at ICDAR 2023
Estimate Trend at a Point in a Noisy Time Series
Code from paper High-throughput Onboard Hyperspectral Image Compression with Ground-based CNN Reconstruction
MIL-RBERT: A Data-driven Approach for Noise Reduction in Distantly Supervised Biomedical Relation Extraction (BioNLP @ ACL 2020)
LeNet5 architecture implementation using pytorch, network parameter optimization and performance evaluation on dataset with Symmetric Label Noise
Self-Supervised Learning for Outlier Detection.
Code for MentorNet: Learning Data-Driven Curriculum for Very Deep Neural Networks
Enhanced awesome-align for low-resource languages and noise simulation: https://arxiv.org/abs/2301.09685
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"
Dynamic Mixing For Speech Processing (mix-on-the-fly)
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.
SMARTboost (boosting of smooth symmetric regression trees)
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."