Noise-Tolerant Paradigm for Training Face Recognition CNNs [Official, CVPR 2019]
-
Updated
Mar 27, 2019 - Python
Noise-Tolerant Paradigm for Training Face Recognition CNNs [Official, CVPR 2019]
A TensorFlow implementation of "Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labels"
Gold Loss Correction for training neural networks with labels corrupted with severe noise
NLNL: Negative Learning for Noisy Labels
Reinforcement Learning with Perturbed Reward, AAAI 2020
Deep Bilevel Learning. In ECCV, 2018.
[ICML2020] Normalized Loss Functions for Deep Learning with Noisy Labels
Shopee Code League 2020 image competition 7th place solution
ICML 2019: Understanding and Utilizing Deep Neural Networks Trained with Noisy Labels
Keras implementation of Training Deep Neural Networks on Noisy Labels with Bootstrapping, Reed et al. 2015
Implementations of different loss-correction techniques to help deep models learn under class-conditional label noise.
MoPro: Webly Supervised Learning
PyTorch implementation of "Contrast to Divide: self-supervised pre-training for learning with noisy labels"
Official Implementation of Unweighted Data Subsampling via Influence Function - AAAI 2020
ICLR 2021: Noise against noise: stochastic label noise helps combat inherent label noise
[MentorMix] "Beyond Synthetic Noise: Deep Learning on Controlled Noisy Labels" implemented in the PyTorch version.
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
Add a description, image, and links to the noisy-labels topic page so that developers can more easily learn about it.
To associate your repository with the noisy-labels topic, visit your repo's landing page and select "manage topics."