Deep adversarial subspace clustering
Most existing subspace clustering methods hinge on self-expression of handcrafted representations and are unaware of potential clustering errors. Thus they perform unsatisfactorily on real data with complex underlying subspaces. To solve this issue, we propose a novel deep adversarial subspace clust...
Saved in:
Main Authors: | , , |
---|---|
Format: | text |
Language: | English |
Published: |
Institutional Knowledge at Singapore Management University
2018
|
Subjects: | |
Online Access: | https://ink.library.smu.edu.sg/sis_research/9001 https://ink.library.smu.edu.sg/context/sis_research/article/10004/viewcontent/2018_CVPR_Adversarial_Subspace__1_.pdf |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Singapore Management University |
Language: | English |
id |
sg-smu-ink.sis_research-10004 |
---|---|
record_format |
dspace |
spelling |
sg-smu-ink.sis_research-100042024-07-25T08:18:30Z Deep adversarial subspace clustering ZHOU, Pan HOU, Yunqing FENG, Jiashi Most existing subspace clustering methods hinge on self-expression of handcrafted representations and are unaware of potential clustering errors. Thus they perform unsatisfactorily on real data with complex underlying subspaces. To solve this issue, we propose a novel deep adversarial subspace clustering (DASC) model, which learns more favorable sample representations by deep learning for subspace clustering, and more importantly introduces adversarial learning to supervise sample representation learning and subspace clustering. Specifically, DASC consists of a subspace clustering generator and a quality-verifying discriminator, which learn against each other. The generator produces subspace estimation and sample clustering. The discriminator evaluates current clustering performance by inspecting whether the re-sampled data from estimated subspaces have consistent subspace properties, and supervises the generator to progressively improve subspace clustering. Experimental results on the handwritten recognition, face and object clustering tasks demonstrate the advantages of DASC over shallow and few deep subspace clustering models. Moreover, to our best knowledge, this is the first successful application of GAN-alike model for unsupervised subspace clustering, which also paves the way for deep learning to solve other unsupervised learning problems. 2018-06-01T07:00:00Z text application/pdf https://ink.library.smu.edu.sg/sis_research/9001 info:doi/10.1109/CVPR.2018.00172 https://ink.library.smu.edu.sg/context/sis_research/article/10004/viewcontent/2018_CVPR_Adversarial_Subspace__1_.pdf http://creativecommons.org/licenses/by-nc-nd/4.0/ Research Collection School Of Computing and Information Systems eng Institutional Knowledge at Singapore Management University Generators Clustering methods Fasteners Task analysis Feeds Estimation Graphics and Human Computer Interfaces |
institution |
Singapore Management University |
building |
SMU Libraries |
continent |
Asia |
country |
Singapore Singapore |
content_provider |
SMU Libraries |
collection |
InK@SMU |
language |
English |
topic |
Generators Clustering methods Fasteners Task analysis Feeds Estimation Graphics and Human Computer Interfaces |
spellingShingle |
Generators Clustering methods Fasteners Task analysis Feeds Estimation Graphics and Human Computer Interfaces ZHOU, Pan HOU, Yunqing FENG, Jiashi Deep adversarial subspace clustering |
description |
Most existing subspace clustering methods hinge on self-expression of handcrafted representations and are unaware of potential clustering errors. Thus they perform unsatisfactorily on real data with complex underlying subspaces. To solve this issue, we propose a novel deep adversarial subspace clustering (DASC) model, which learns more favorable sample representations by deep learning for subspace clustering, and more importantly introduces adversarial learning to supervise sample representation learning and subspace clustering. Specifically, DASC consists of a subspace clustering generator and a quality-verifying discriminator, which learn against each other. The generator produces subspace estimation and sample clustering. The discriminator evaluates current clustering performance by inspecting whether the re-sampled data from estimated subspaces have consistent subspace properties, and supervises the generator to progressively improve subspace clustering. Experimental results on the handwritten recognition, face and object clustering tasks demonstrate the advantages of DASC over shallow and few deep subspace clustering models. Moreover, to our best knowledge, this is the first successful application of GAN-alike model for unsupervised subspace clustering, which also paves the way for deep learning to solve other unsupervised learning problems. |
format |
text |
author |
ZHOU, Pan HOU, Yunqing FENG, Jiashi |
author_facet |
ZHOU, Pan HOU, Yunqing FENG, Jiashi |
author_sort |
ZHOU, Pan |
title |
Deep adversarial subspace clustering |
title_short |
Deep adversarial subspace clustering |
title_full |
Deep adversarial subspace clustering |
title_fullStr |
Deep adversarial subspace clustering |
title_full_unstemmed |
Deep adversarial subspace clustering |
title_sort |
deep adversarial subspace clustering |
publisher |
Institutional Knowledge at Singapore Management University |
publishDate |
2018 |
url |
https://ink.library.smu.edu.sg/sis_research/9001 https://ink.library.smu.edu.sg/context/sis_research/article/10004/viewcontent/2018_CVPR_Adversarial_Subspace__1_.pdf |
_version_ |
1814047688696528896 |