Uncertainty Based Detection and Relabeling of Noisy Image Labels
arXiv:1906.11876
Abstract
Deep neural networks (DNNs) are powerful tools in computer vision tasks. However, in many realistic scenarios label noise is prevalent in the training images, and overfitting to these noisy labels can significantly harm the generalization performance of DNNs. We propose a novel technique to identify data with noisy labels based on the different distributions of the predictive uncertainties from a DNN over the clean and noisy data. Additionally, the behavior of the uncertainty over the course of training helps to identify the network weights which best can be used to relabel the noisy labels. Data with noisy labels can therefore be cleaned in an iterative process. Our proposed method can be easily implemented, and shows promising performance on the task of noisy label detection on CIFAR-10 and CIFAR-100.
arXiv commentUncertainty and Robustness in Deep Visual Learning Workshop at CVPR 2019
References in corpus (13)
- A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks
- Learning to Reweight Examples for Robust Deep Learning
- Classification with Noisy Labels by Importance Reweighting
- Training Deep Neural Networks on Noisy Labels with Bootstrapping
- MentorNet: Learning Data-Driven Curriculum for Very Deep Neural Networks on Corrupted Labels
- Training Convolutional Networks with Noisy Labels
- Bayesian Active Learning for Classification and Preference Learning
- Detecting Adversarial Samples from Artifacts
- Dimensionality-Driven Learning with Noisy Labels
- Unsupervised Label Noise Modeling and Loss Correction
- Understanding Measures of Uncertainty for Adversarial Example Detection
- Adversarial Phenomenon in the Eyes of Bayesian Deep Learning
- Auxiliary Image Regularization for Deep CNNs with Noisy Labels