NoiseRank: Unsupervised Label Noise Reduction with Dependence Models release_3ziauerfuzagpcor4n4gmanu4u

by Karishma Sharma, Pinar Donmez, Enming Luo, Yan Liu, I. Zeki Yalniz

Released as a article .

2020  

Abstract

Label noise is increasingly prevalent in datasets acquired from noisy channels. Existing approaches that detect and remove label noise generally rely on some form of supervision, which is not scalable and error-prone. In this paper, we propose NoiseRank, for unsupervised label noise reduction using Markov Random Fields (MRF). We construct a dependence model to estimate the posterior probability of an instance being incorrectly labeled given the dataset, and rank instances based on their estimated probabilities. Our method 1) Does not require supervision from ground-truth labels, or priors on label or noise distribution. 2) It is interpretable by design, enabling transparency in label noise removal. 3) It is agnostic to classifier architecture/optimization framework and content modality. These advantages enable wide applicability in real noise settings, unlike prior works constrained by one or more conditions. NoiseRank improves state-of-the-art classification on Food101-N (~20% noise), and is effective on high noise Clothing-1M (~40% noise).
In text/plain format

Archived Files and Locations

application/pdf  2.6 MB
file_pcdodgvbebdslkvu75jxfx5fqm
arxiv.org (repository)
web.archive.org (webarchive)
Read Archived PDF
Preserved and Accessible
Type  article
Stage   submitted
Date   2020-03-15
Version   v1
Language   en ?
arXiv  2003.06729v1
Work Entity
access all versions, variants, and formats of this works (eg, pre-prints)
Catalog Record
Revision: fdca14c4-29b7-4b9d-85d0-8105a05532f8
API URL: JSON