Unsupervised Deep Embedding for Clustering Analysis. Xie, J., Edu, J., W., Girshick, R., Farhadi, A., & Edu, A., W.
![Unsupervised Deep Embedding for Clustering Analysis [pdf]](https://bibbase.org/img/filetypes/pdf.svg "pdf")
Paper Website abstract bibtex
Paper Website abstract bibtex Clustering is central to many data-driven appli-cation domains and has been studied extensively in terms of distance functions and grouping al-gorithms. Relatively little work has focused on learning representations for clustering. In this paper, we propose Deep Embedded Clustering (DEC), a method that simultaneously learns fea-ture representations and cluster assignments us-ing deep neural networks. DEC learns a map-ping from the data space to a lower-dimensional feature space in which it iteratively optimizes a clustering objective. Our experimental evalua-tions on image and text corpora show significant improvement over state-of-the-art methods.
@article{
title = {Unsupervised Deep Embedding for Clustering Analysis},
type = {article},
websites = {http://proceedings.mlr.press/v48/xieb16.pdf},
id = {eaca8716-b3b8-3b2d-81af-036466551755},
created = {2018-02-05T19:16:41.582Z},
accessed = {2018-02-05},
file_attached = {true},
profile_id = {371589bb-c770-37ff-8193-93c6f25ffeb1},
group_id = {f982cd63-7ceb-3aa2-ac7e-a953963d6716},
last_modified = {2018-02-05T19:16:45.446Z},
read = {false},
starred = {false},
authored = {false},
confirmed = {false},
hidden = {false},
private_publication = {false},
abstract = {Clustering is central to many data-driven appli-cation domains and has been studied extensively in terms of distance functions and grouping al-gorithms. Relatively little work has focused on learning representations for clustering. In this paper, we propose Deep Embedded Clustering (DEC), a method that simultaneously learns fea-ture representations and cluster assignments us-ing deep neural networks. DEC learns a map-ping from the data space to a lower-dimensional feature space in which it iteratively optimizes a clustering objective. Our experimental evalua-tions on image and text corpora show significant improvement over state-of-the-art methods.},
bibtype = {article},
author = {Xie, Junyuan and Edu, Jxie@cs Washington and Girshick, Ross and Farhadi, Ali and Edu, Ali@cs Washington}
}Downloads: 0
{"_id":"4A8FqbRw42ME4PctD","bibbaseid":"xie-edu-girshick-farhadi-edu-unsuperviseddeepembeddingforclusteringanalysis","downloads":0,"creationDate":"2018-02-07T16:22:57.347Z","title":"Unsupervised Deep Embedding for Clustering Analysis","author_short":["Xie, J.","Edu, J., W.","Girshick, R.","Farhadi, A.","Edu, A., W."],"year":null,"bibtype":"article","biburl":null,"bibdata":{"title":"Unsupervised Deep Embedding for Clustering Analysis","type":"article","websites":"http://proceedings.mlr.press/v48/xieb16.pdf","id":"eaca8716-b3b8-3b2d-81af-036466551755","created":"2018-02-05T19:16:41.582Z","accessed":"2018-02-05","file_attached":"true","profile_id":"371589bb-c770-37ff-8193-93c6f25ffeb1","group_id":"f982cd63-7ceb-3aa2-ac7e-a953963d6716","last_modified":"2018-02-05T19:16:45.446Z","read":false,"starred":false,"authored":false,"confirmed":false,"hidden":false,"private_publication":false,"abstract":"Clustering is central to many data-driven appli-cation domains and has been studied extensively in terms of distance functions and grouping al-gorithms. Relatively little work has focused on learning representations for clustering. In this paper, we propose Deep Embedded Clustering (DEC), a method that simultaneously learns fea-ture representations and cluster assignments us-ing deep neural networks. DEC learns a map-ping from the data space to a lower-dimensional feature space in which it iteratively optimizes a clustering objective. Our experimental evalua-tions on image and text corpora show significant improvement over state-of-the-art methods.","bibtype":"article","author":"Xie, Junyuan and Edu, Jxie@cs Washington and Girshick, Ross and Farhadi, Ali and Edu, Ali@cs Washington","bibtex":"@article{\n title = {Unsupervised Deep Embedding for Clustering Analysis},\n type = {article},\n websites = {http://proceedings.mlr.press/v48/xieb16.pdf},\n id = {eaca8716-b3b8-3b2d-81af-036466551755},\n created = {2018-02-05T19:16:41.582Z},\n accessed = {2018-02-05},\n file_attached = {true},\n profile_id = {371589bb-c770-37ff-8193-93c6f25ffeb1},\n group_id = {f982cd63-7ceb-3aa2-ac7e-a953963d6716},\n last_modified = {2018-02-05T19:16:45.446Z},\n read = {false},\n starred = {false},\n authored = {false},\n confirmed = {false},\n hidden = {false},\n private_publication = {false},\n abstract = {Clustering is central to many data-driven appli-cation domains and has been studied extensively in terms of distance functions and grouping al-gorithms. Relatively little work has focused on learning representations for clustering. In this paper, we propose Deep Embedded Clustering (DEC), a method that simultaneously learns fea-ture representations and cluster assignments us-ing deep neural networks. DEC learns a map-ping from the data space to a lower-dimensional feature space in which it iteratively optimizes a clustering objective. Our experimental evalua-tions on image and text corpora show significant improvement over state-of-the-art methods.},\n bibtype = {article},\n author = {Xie, Junyuan and Edu, Jxie@cs Washington and Girshick, Ross and Farhadi, Ali and Edu, Ali@cs Washington}\n}","author_short":["Xie, J.","Edu, J., W.","Girshick, R.","Farhadi, A.","Edu, A., W."],"urls":{"Paper":"http://bibbase.org/service/mendeley/371589bb-c770-37ff-8193-93c6f25ffeb1/file/243431cd-6773-b179-6eac-a4a3f35fb8a7/Unsupervised_Deep_Embedding_for_Clustering_Analysis.pdf.pdf","Website":"http://proceedings.mlr.press/v48/xieb16.pdf"},"bibbaseid":"xie-edu-girshick-farhadi-edu-unsuperviseddeepembeddingforclusteringanalysis","role":"author","downloads":0},"search_terms":["unsupervised","deep","embedding","clustering","analysis","xie","edu","girshick","farhadi","edu"],"keywords":[],"authorIDs":[]}