Peerannot: classification for crowdsourced image datasets with Python
-
Updated
May 17, 2024 - Python
Peerannot: classification for crowdsourced image datasets with Python
Effective and Robust Adversarial Training Against Data and Label Corruptions
[NeurIPSW 2022] On the Ramifications of Human Label Uncertainty
Implementations of different loss-correction techniques to help deep models learn under class-conditional label noise.
[ACM MM 2021 Oral Presentation] A unified framework for co-training-based noisy label learning methods.
for KCC 2022 Paper (Outstanding Paper Award)
[NeurIPSW 2022] On the Ramifications of Human Label Uncertainty
This repository implements conformal prediction methods for classification tasks that can automatically adapt to random label contamination in the calibration sample.
PyTorch Implementation of Robust Cross Entropy Loss (Loss Correction for Label Noise)
Supplementary material and code for "Mitigating Label Noise through Data Ambiguation" as published at AAAI 2024.
Double Descent results for FCNNs on MNIST, extended by Label Noise (Reconciling Modern Machine-Learning Practice and the Classical Bias–Variance Trade-Off) [Python/PyTorch]..
This is the source code for Butterfly: One-step Approach towards Wildly Unsupervised Domain Adaptation (NeurIPS'19 Workshop).
Code and data for the WWW 2021 research-track paper: Typing Errors in Factual Knowledge Graphs: Severity and Possible Ways Out
Challenging label noise called BadLabel; Robust label-noise learning called Robust DivideMix
SREA: Self-Re-Labeling with Embedding Analysis
[NeurIPS 2023] "Combating Bilateral Edge Noise for Robust Link Prediction"
[NeurIPS 2023] Combating Bilateral Edge Noise for Robust Link Prediction
A Python Library for Biquality Learning
Official implementation of "An Action Is Worth Multiple Words: Handling Ambiguity in Action Recognition", BMVC 2022
Add a description, image, and links to the label-noise topic page so that developers can more easily learn about it.
To associate your repository with the label-noise topic, visit your repo's landing page and select "manage topics."