@inproceedings{dravid2022investigating,
abstract = {Generative Adversarial Networks (GANs) have shown promise in augmenting datasets and boosting convolutional neural network (CNN) performance on image classification tasks. But they introduce more hyperparameters to tune as well as the need for additional time and computational power to train, supplementary to the CNN. In this work, we examine the potential for Auxiliary-Classifier GANs (AC-GANs) as a'one-stop-shop' architecture for image classification, particularly in low data regimes. Additionally, we explore modifications to the typical AC-GAN framework, changing the generator's latent space sampling scheme and employing a Wasserstein loss with gradient penalty to stabilize the simultaneous training of image synthesis and classification. Through experiments on images of varying resolutions and complexity, we demonstrate that AC-GANs show promise in image classification, achieving competitive performance with standard CNNs. These methods can be employed as an'all-in-one' framework with particular utility in the absence of large amounts of training data.},
archivePrefix = {arXiv},
arxivId = {2201.09120},
author = {Dravid, Amil and Schiffers, Florian and Wu, Yunan and Cossairt, Oliver and Katsaggelos, Aggelos K.},
booktitle = {ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
doi = {10.1109/ICASSP43922.2022.9747286},
eprint = {2201.09120},
isbn = {978-1-6654-0540-9},
issn = {15206149},
keywords = {Convolutional Neural Networks,Data Augmentation,Deep Learning,Generative Adversarial Networks,Image Classification},
month = {may},
organization = {IEEE},
pages = {3318--3322},
publisher = {IEEE},
title = {{Investigating the Potential of Auxiliary-Classifier Gans for Image Classification in Low Data Regimes}},
url = {https://ieeexplore.ieee.org/document/9747286/},
volume = {2022-May},
year = {2022}
}

{"_id":"9B8sBjQr3iDe292rZ","bibbaseid":"dravid-schiffers-wu-cossairt-katsaggelos-investigatingthepotentialofauxiliaryclassifiergansforimageclassificationinlowdataregimes-2022","author_short":["Dravid, A.","Schiffers, F.","Wu, Y.","Cossairt, O.","Katsaggelos, A. K."],"bibdata":{"bibtype":"inproceedings","type":"inproceedings","abstract":"Generative Adversarial Networks (GANs) have shown promise in augmenting datasets and boosting convolutional neural network (CNN) performance on image classification tasks. But they introduce more hyperparameters to tune as well as the need for additional time and computational power to train, supplementary to the CNN. In this work, we examine the potential for Auxiliary-Classifier GANs (AC-GANs) as a'one-stop-shop' architecture for image classification, particularly in low data regimes. Additionally, we explore modifications to the typical AC-GAN framework, changing the generator's latent space sampling scheme and employing a Wasserstein loss with gradient penalty to stabilize the simultaneous training of image synthesis and classification. Through experiments on images of varying resolutions and complexity, we demonstrate that AC-GANs show promise in image classification, achieving competitive performance with standard CNNs. These methods can be employed as an'all-in-one' framework with particular utility in the absence of large amounts of training data.","archiveprefix":"arXiv","arxivid":"2201.09120","author":[{"propositions":[],"lastnames":["Dravid"],"firstnames":["Amil"],"suffixes":[]},{"propositions":[],"lastnames":["Schiffers"],"firstnames":["Florian"],"suffixes":[]},{"propositions":[],"lastnames":["Wu"],"firstnames":["Yunan"],"suffixes":[]},{"propositions":[],"lastnames":["Cossairt"],"firstnames":["Oliver"],"suffixes":[]},{"propositions":[],"lastnames":["Katsaggelos"],"firstnames":["Aggelos","K."],"suffixes":[]}],"booktitle":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","doi":"10.1109/ICASSP43922.2022.9747286","eprint":"2201.09120","isbn":"978-1-6654-0540-9","issn":"15206149","keywords":"Convolutional Neural Networks,Data Augmentation,Deep Learning,Generative Adversarial Networks,Image Classification","month":"may","organization":"IEEE","pages":"3318–3322","publisher":"IEEE","title":"Investigating the Potential of Auxiliary-Classifier Gans for Image Classification in Low Data Regimes","url":"https://ieeexplore.ieee.org/document/9747286/","volume":"2022-May","year":"2022","bibtex":"@inproceedings{dravid2022investigating,\nabstract = {Generative Adversarial Networks (GANs) have shown promise in augmenting datasets and boosting convolutional neural network (CNN) performance on image classification tasks. But they introduce more hyperparameters to tune as well as the need for additional time and computational power to train, supplementary to the CNN. In this work, we examine the potential for Auxiliary-Classifier GANs (AC-GANs) as a'one-stop-shop' architecture for image classification, particularly in low data regimes. Additionally, we explore modifications to the typical AC-GAN framework, changing the generator's latent space sampling scheme and employing a Wasserstein loss with gradient penalty to stabilize the simultaneous training of image synthesis and classification. Through experiments on images of varying resolutions and complexity, we demonstrate that AC-GANs show promise in image classification, achieving competitive performance with standard CNNs. These methods can be employed as an'all-in-one' framework with particular utility in the absence of large amounts of training data.},\narchivePrefix = {arXiv},\narxivId = {2201.09120},\nauthor = {Dravid, Amil and Schiffers, Florian and Wu, Yunan and Cossairt, Oliver and Katsaggelos, Aggelos K.},\nbooktitle = {ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},\ndoi = {10.1109/ICASSP43922.2022.9747286},\neprint = {2201.09120},\nisbn = {978-1-6654-0540-9},\nissn = {15206149},\nkeywords = {Convolutional Neural Networks,Data Augmentation,Deep Learning,Generative Adversarial Networks,Image Classification},\nmonth = {may},\norganization = {IEEE},\npages = {3318--3322},\npublisher = {IEEE},\ntitle = {{Investigating the Potential of Auxiliary-Classifier Gans for Image Classification in Low Data Regimes}},\nurl = {https://ieeexplore.ieee.org/document/9747286/},\nvolume = {2022-May},\nyear = {2022}\n}\n","author_short":["Dravid, A.","Schiffers, F.","Wu, Y.","Cossairt, O.","Katsaggelos, A. K."],"key":"dravid2022investigating","id":"dravid2022investigating","bibbaseid":"dravid-schiffers-wu-cossairt-katsaggelos-investigatingthepotentialofauxiliaryclassifiergansforimageclassificationinlowdataregimes-2022","role":"author","urls":{"Paper":"https://ieeexplore.ieee.org/document/9747286/"},"keyword":["Convolutional Neural Networks","Data Augmentation","Deep Learning","Generative Adversarial Networks","Image Classification"],"metadata":{"authorlinks":{}}},"bibtype":"inproceedings","biburl":"https://sites.northwestern.edu/ivpl/files/2023/06/IVPL_Updated_publications-1.bib","dataSources":["KTWAakbPXLGfYseXn","ePKPjG8C6yvpk4mEK","ya2CyA73rpZseyrZ8","37Qfzv6wRptYkoSCL","zFPgsTDAW8aDnb5iN","E6Bth2QB5BYjBMZE7","nbnEjsN7MJhurAK9x","PNQZj6FjzoxxJk4Yi","7FpDWDGJ4KgpDiGfB","bod9ms4MQJHuJgPpp","QR9t5P2cLdJuzhfzK","D8k2SxfC5dKNRFgro","7Dwzbxq93HWrJEhT6","qhF8zxmGcJfvtdeAg","fvDEHD49E2ZRwE3fb","H7crv8NWhZup4d4by","DHqokWsryttGh7pJE","vRJd4wNg9HpoZSMHD","sYxQ6pxFgA59JRhxi","w2WahSbYrbcCKBDsC","XasdXLL99y5rygCmq","3gkSihZQRfAD2KBo3","t5XMbyZbtPBo4wBGS","bEpHM2CtrwW2qE8FP","teJzFLHexaz5AQW5z"],"keywords":["convolutional neural networks","data augmentation","deep learning","generative adversarial networks","image classification"],"search_terms":["investigating","potential","auxiliary","classifier","gans","image","classification","low","data","regimes","dravid","schiffers","wu","cossairt","katsaggelos"],"title":"Investigating the Potential of Auxiliary-Classifier Gans for Image Classification in Low Data Regimes","year":2022}