paper-with-me

홈 › Papers

Logistic-Normal Likelihoods for Heteroscedastic Label Noise

2023-04-06 · Erik Englesson, Amir Mehrpanah, Hossein Azizpour

A natural way of estimating heteroscedastic label noise in regression is to model the observed (potentially noisy) target as a sample from a normal distribution, whose parameters can be learned by minimizing the negative log-likelihood. This formulation has desirable loss attenuation properties, as it reduces the contribution of high-error examples. Intuitively, this behavior can improve robustness against label noise by reducing overfitting. We propose an extension of this simple and probabilistic approach to classification that has the same desirable loss attenuation properties. Furthermore, we discuss and address some practical challenges of this extension. We evaluate the effectiveness of the method by measuring its robustness against label noise in classification. We perform enlightening experiments exploring the inner workings of the method, including sensitivity to hyperparameters, ablation studies, and other insightful analyses.

📄 PDF Abstract BibTeX arXiv:2304.02849

Code (1)

erikenglesson/logistic-normal 공식 구현 tf

Tasks

Classification

Similar Papers 제목 키워드 기반

Variational Variance: Simple, Reliable, Calibrated Heteroscedastic Noise Variance Parameterization

2020-06-08 · Andrew Stirn, David A. Knowles

Brittle optimization has been observed to adversely impact model likelihoods for regression and VAEs when simultaneously fitting neural network mappings from a (random) variable onto the mean and variance of a dependent …

regression

Active Heteroscedastic Regression

2017-08-01 · ICML 2017 8 · Kamalika Chaudhuri, Prateek Jain, Nagarajan Natarajan

An active learner is given a model class $\Theta$, a large sample of unlabeled data drawn from an underlying distribution and access to a labeling oracle that can provide a label for any of the unlabeled instances. …

Active LearningBinary Classificationregression

Nonparametric Deconvolution and Denoising using Simulation Based Inference

2026-06-20 · Ritwik Vashistha, Abhra Sarkar, Arya Farahi arxiv

Latent signals are often obscured by measurement noise, yet encode the underlying laws and dynamics of complex systems; learning both the signals and their distributions remains a central challenge in scientific inferenc…

A Simple Probabilistic Method for Deep Classification under Input-Dependent Label Noise

2020-03-15 · Mark Collier, Basil Mustafa, Efi Kokiopoulou, Rodolphe Jenatton 외

Datasets with noisy labels are a common occurrence in practical applications of classification methods. We propose a simple probabilistic method for training deep classifiers under input-dependent (heteroscedastic) label…

General Classificationimage-classificationImage ClassificationImage Segmentation+1

Correlated Input-Dependent Label Noise in Large-Scale Image Classification

2021-05-19 · CVPR 2021 1 · Mark Collier, Basil Mustafa, Efi Kokiopoulou, Rodolphe Jenatton 외

Large scale image classification datasets often contain noisy labels. We take a principled probabilistic approach to modelling input-dependent, also known as heteroscedastic, label noise in these datasets. We place a mul…

Classificationimage-classificationImage Classification