Direct: Deep Discriminative Embedding for Clustering of Ligo Data. Bahaadini, S., Rohani, N., Katsaggelos, A., Noroozi, V., Coughlin, S., & Zevin, M. In 2018 25th IEEE International Conference on Image Processing (ICIP), pages 748–752, oct, 2018. IEEE, IEEE. ![Direct: Deep Discriminative Embedding for Clustering of Ligo Data [link]](https://bibbase.org/img/filetypes/link.svg "link")
Paper doi abstract bibtex In this paper, benefiting from the strong ability of deep neural network in estimating non-linear functions, we propose a discriminative embedding function to be used as a feature extractor for clustering tasks. The trained embedding function transfers knowledge from the domain of a labeled set of morphologically-distinct images, known as classes, to a new domain within which new classes can potentially be isolated and identified. Our target application in this paper is the Gravity Spy Project, which is an effort to characterize transient, non-Gaussian noise present in data from the Advanced Laser Interferometer Gravitational-wave Observatory, or LIGO. Accumulating large, labeled sets of noise features and identifying of new classes of noise lead to a better understanding of their origin, which makes their removal from the data and/or detectors possible.
@inproceedings{bahaadini2018direct,
abstract = {In this paper, benefiting from the strong ability of deep neural network in estimating non-linear functions, we propose a discriminative embedding function to be used as a feature extractor for clustering tasks. The trained embedding function transfers knowledge from the domain of a labeled set of morphologically-distinct images, known as classes, to a new domain within which new classes can potentially be isolated and identified. Our target application in this paper is the Gravity Spy Project, which is an effort to characterize transient, non-Gaussian noise present in data from the Advanced Laser Interferometer Gravitational-wave Observatory, or LIGO. Accumulating large, labeled sets of noise features and identifying of new classes of noise lead to a better understanding of their origin, which makes their removal from the data and/or detectors possible.},
archivePrefix = {arXiv},
arxivId = {1805.02296},
author = {Bahaadini, S. and Rohani, N. and Katsaggelos, A.K. and Noroozi, V. and Coughlin, S. and Zevin, M.},
booktitle = {2018 25th IEEE International Conference on Image Processing (ICIP)},
doi = {10.1109/ICIP.2018.8451708},
eprint = {1805.02296},
isbn = {978-1-4799-7061-2},
issn = {15224880},
keywords = {Deep Learning,Domain adaptation,Image Clustering,LIGO},
month = {oct},
organization = {IEEE},
pages = {748--752},
publisher = {IEEE},
title = {{Direct: Deep Discriminative Embedding for Clustering of Ligo Data}},
url = {https://ieeexplore.ieee.org/document/8451708/},
year = {2018}
}
Downloads: 0
{"_id":"SuvSkWS7Hze2GDEES","bibbaseid":"bahaadini-rohani-katsaggelos-noroozi-coughlin-zevin-directdeepdiscriminativeembeddingforclusteringofligodata-2018","author_short":["Bahaadini, S.","Rohani, N.","Katsaggelos, A.","Noroozi, V.","Coughlin, S.","Zevin, M."],"bibdata":{"bibtype":"inproceedings","type":"inproceedings","abstract":"In this paper, benefiting from the strong ability of deep neural network in estimating non-linear functions, we propose a discriminative embedding function to be used as a feature extractor for clustering tasks. The trained embedding function transfers knowledge from the domain of a labeled set of morphologically-distinct images, known as classes, to a new domain within which new classes can potentially be isolated and identified. Our target application in this paper is the Gravity Spy Project, which is an effort to characterize transient, non-Gaussian noise present in data from the Advanced Laser Interferometer Gravitational-wave Observatory, or LIGO. Accumulating large, labeled sets of noise features and identifying of new classes of noise lead to a better understanding of their origin, which makes their removal from the data and/or detectors possible.","archiveprefix":"arXiv","arxivid":"1805.02296","author":[{"propositions":[],"lastnames":["Bahaadini"],"firstnames":["S."],"suffixes":[]},{"propositions":[],"lastnames":["Rohani"],"firstnames":["N."],"suffixes":[]},{"propositions":[],"lastnames":["Katsaggelos"],"firstnames":["A.K."],"suffixes":[]},{"propositions":[],"lastnames":["Noroozi"],"firstnames":["V."],"suffixes":[]},{"propositions":[],"lastnames":["Coughlin"],"firstnames":["S."],"suffixes":[]},{"propositions":[],"lastnames":["Zevin"],"firstnames":["M."],"suffixes":[]}],"booktitle":"2018 25th IEEE International Conference on Image Processing (ICIP)","doi":"10.1109/ICIP.2018.8451708","eprint":"1805.02296","isbn":"978-1-4799-7061-2","issn":"15224880","keywords":"Deep Learning,Domain adaptation,Image Clustering,LIGO","month":"oct","organization":"IEEE","pages":"748–752","publisher":"IEEE","title":"Direct: Deep Discriminative Embedding for Clustering of Ligo Data","url":"https://ieeexplore.ieee.org/document/8451708/","year":"2018","bibtex":"@inproceedings{bahaadini2018direct,\nabstract = {In this paper, benefiting from the strong ability of deep neural network in estimating non-linear functions, we propose a discriminative embedding function to be used as a feature extractor for clustering tasks. The trained embedding function transfers knowledge from the domain of a labeled set of morphologically-distinct images, known as classes, to a new domain within which new classes can potentially be isolated and identified. Our target application in this paper is the Gravity Spy Project, which is an effort to characterize transient, non-Gaussian noise present in data from the Advanced Laser Interferometer Gravitational-wave Observatory, or LIGO. Accumulating large, labeled sets of noise features and identifying of new classes of noise lead to a better understanding of their origin, which makes their removal from the data and/or detectors possible.},\narchivePrefix = {arXiv},\narxivId = {1805.02296},\nauthor = {Bahaadini, S. and Rohani, N. and Katsaggelos, A.K. and Noroozi, V. and Coughlin, S. and Zevin, M.},\nbooktitle = {2018 25th IEEE International Conference on Image Processing (ICIP)},\ndoi = {10.1109/ICIP.2018.8451708},\neprint = {1805.02296},\nisbn = {978-1-4799-7061-2},\nissn = {15224880},\nkeywords = {Deep Learning,Domain adaptation,Image Clustering,LIGO},\nmonth = {oct},\norganization = {IEEE},\npages = {748--752},\npublisher = {IEEE},\ntitle = {{Direct: Deep Discriminative Embedding for Clustering of Ligo Data}},\nurl = {https://ieeexplore.ieee.org/document/8451708/},\nyear = {2018}\n}\n","author_short":["Bahaadini, S.","Rohani, N.","Katsaggelos, A.","Noroozi, V.","Coughlin, S.","Zevin, M."],"key":"bahaadini2018direct","id":"bahaadini2018direct","bibbaseid":"bahaadini-rohani-katsaggelos-noroozi-coughlin-zevin-directdeepdiscriminativeembeddingforclusteringofligodata-2018","role":"author","urls":{"Paper":"https://ieeexplore.ieee.org/document/8451708/"},"keyword":["Deep Learning","Domain adaptation","Image Clustering","LIGO"],"metadata":{"authorlinks":{}}},"bibtype":"inproceedings","biburl":"https://sites.northwestern.edu/ivpl/files/2023/06/IVPL_Updated_publications-1.bib","dataSources":["KTWAakbPXLGfYseXn","ePKPjG8C6yvpk4mEK","37Qfzv6wRptYkoSCL","zFPgsTDAW8aDnb5iN","E6Bth2QB5BYjBMZE7","nbnEjsN7MJhurAK9x","PNQZj6FjzoxxJk4Yi","7FpDWDGJ4KgpDiGfB","bod9ms4MQJHuJgPpp","QR9t5P2cLdJuzhfzK","D8k2SxfC5dKNRFgro","7Dwzbxq93HWrJEhT6","qhF8zxmGcJfvtdeAg","fvDEHD49E2ZRwE3fb","H7crv8NWhZup4d4by","DHqokWsryttGh7pJE","vRJd4wNg9HpoZSMHD","sYxQ6pxFgA59JRhxi","w2WahSbYrbcCKBDsC","XasdXLL99y5rygCmq","3gkSihZQRfAD2KBo3","t5XMbyZbtPBo4wBGS","bEpHM2CtrwW2qE8FP","teJzFLHexaz5AQW5z"],"keywords":["deep learning","domain adaptation","image clustering","ligo"],"search_terms":["direct","deep","discriminative","embedding","clustering","ligo","data","bahaadini","rohani","katsaggelos","noroozi","coughlin","zevin"],"title":"Direct: Deep Discriminative Embedding for Clustering of Ligo Data","year":2018}