Using WGAN for Improving Imbalanced Classification Performance. Bhatia, S. & Dahyot, R. In Curry, E., Keane, M., Ojo, A., & Salwala, D., editors, 27th Irish Conference on Artificial Intelligence and Cognitive Science, pages 365-375, Galway, Ireland, 2019.
![Using WGAN for Improving Imbalanced Classification Performance [pdf]](https://bibbase.org/img/filetypes/pdf.svg "pdf")
Paper abstract bibtex
Paper abstract bibtex This paper investigates data synthesis with a Generative Adversarial Network (GAN) for augmenting the amount of data used for training classifiers (in supervised learning) to compensate for class imbalance (when the classes are not represented equally by the same number of training samples). Our data synthesis approach with GAN is compared with data augmentation in the context of image classification. Our experimental results show encouraging results in comparison to standard data augmentation schemes based on image transforms.
@inproceedings{Bhatia2019,
title = {Using WGAN for Improving Imbalanced Classification Performance},
author = {S. Bhatia and R. Dahyot},
booktitle = {27th Irish Conference on Artificial Intelligence and Cognitive Science},
address = {Galway, Ireland},
issn = {1613-0073},
year = {2019},
editor = {Edward Curry and Mark Keane and Adegboyega Ojo and Dhaval Salwala},
pages = {365-375},
abstract = {This paper investigates data synthesis with a Generative Adversarial Network (GAN) for augmenting the amount of data used for
training classifiers (in supervised learning) to compensate for class imbalance (when the classes are not represented equally by the same number of
training samples). Our data synthesis approach with GAN is compared
with data augmentation in the context of image classification. Our experimental results show encouraging results in comparison to standard
data augmentation schemes based on image transforms.},
url = {http://ceur-ws.org/Vol-2563/aics_34.pdf}}Downloads: 0
{"_id":"x6zQh9hTrrbfmrFRy","bibbaseid":"bhatia-dahyot-usingwganforimprovingimbalancedclassificationperformance-2019","authorIDs":["6fptrFgK7WSZkf6TM"],"author_short":["Bhatia, S.","Dahyot, R."],"bibdata":{"bibtype":"inproceedings","type":"inproceedings","title":"Using WGAN for Improving Imbalanced Classification Performance","author":[{"firstnames":["S."],"propositions":[],"lastnames":["Bhatia"],"suffixes":[]},{"firstnames":["R."],"propositions":[],"lastnames":["Dahyot"],"suffixes":[]}],"booktitle":"27th Irish Conference on Artificial Intelligence and Cognitive Science","address":"Galway, Ireland","issn":"1613-0073","year":"2019","editor":[{"firstnames":["Edward"],"propositions":[],"lastnames":["Curry"],"suffixes":[]},{"firstnames":["Mark"],"propositions":[],"lastnames":["Keane"],"suffixes":[]},{"firstnames":["Adegboyega"],"propositions":[],"lastnames":["Ojo"],"suffixes":[]},{"firstnames":["Dhaval"],"propositions":[],"lastnames":["Salwala"],"suffixes":[]}],"pages":"365-375","abstract":"This paper investigates data synthesis with a Generative Adversarial Network (GAN) for augmenting the amount of data used for training classifiers (in supervised learning) to compensate for class imbalance (when the classes are not represented equally by the same number of training samples). Our data synthesis approach with GAN is compared with data augmentation in the context of image classification. Our experimental results show encouraging results in comparison to standard data augmentation schemes based on image transforms.","url":"http://ceur-ws.org/Vol-2563/aics_34.pdf","bibtex":"@inproceedings{Bhatia2019, \ntitle = {Using WGAN for Improving Imbalanced Classification Performance}, \nauthor = {S. Bhatia and R. Dahyot}, \nbooktitle = {27th Irish Conference on Artificial Intelligence and Cognitive Science}, \naddress = {Galway, Ireland}, \nissn = {1613-0073},\nyear = {2019}, \neditor = {Edward Curry and Mark Keane and Adegboyega Ojo and Dhaval Salwala}, \npages = {365-375}, \nabstract = {This paper investigates data synthesis with a Generative Adversarial Network (GAN) for augmenting the amount of data used for\ntraining classifiers (in supervised learning) to compensate for class imbalance (when the classes are not represented equally by the same number of\ntraining samples). Our data synthesis approach with GAN is compared\nwith data augmentation in the context of image classification. Our experimental results show encouraging results in comparison to standard\ndata augmentation schemes based on image transforms.},\nurl = {http://ceur-ws.org/Vol-2563/aics_34.pdf}}\n\n","author_short":["Bhatia, S.","Dahyot, R."],"editor_short":["Curry, E.","Keane, M.","Ojo, A.","Salwala, D."],"key":"Bhatia2019","id":"Bhatia2019","bibbaseid":"bhatia-dahyot-usingwganforimprovingimbalancedclassificationperformance-2019","role":"author","urls":{"Paper":"http://ceur-ws.org/Vol-2563/aics_34.pdf"},"metadata":{"authorlinks":{"dahyot, r":"https://roznn.github.io/ipublication.html"}},"downloads":0},"bibtype":"inproceedings","biburl":"https://raw.githubusercontent.com/Roznn/Roznn.github.io/master/works.bib","creationDate":"2021-01-17T18:19:29.521Z","downloads":0,"keywords":[],"search_terms":["using","wgan","improving","imbalanced","classification","performance","bhatia","dahyot"],"title":"Using WGAN for Improving Imbalanced Classification Performance","year":2019,"dataSources":["LyGNQYGRFw8k9gPrK","dtJ7afty6nTMHhqAE"]}