Deep Embedded Clustering with Data Augmentation

Xifeng Guo, En Zhu, Xinwang Liu, Jianping Yin
Proceedings of The 10th Asian Conference on Machine Learning, PMLR 95:550-565, 2018.

Abstract

Deep Embedded Clustering (DEC) surpasses traditional clustering algorithms by jointly performing feature learning and cluster assignment. Although a lot of variants have emerged, they all ignore a crucial ingredient, \emph{data augmentation}, which has been widely employed in supervised deep learning models to improve the generalization. To fill this gap, in this paper, we propose the framework of Deep Embedded Clustering with Data Augmentation (DEC-DA). Specifically, we first train an autoencoder with the augmented data to construct the initial feature space. Then we constrain the embedded features with a clustering loss to further learn clustering-oriented features. The clustering loss is composed of the target (pseudo label) and the actual output of the feature learning model, where the target is computed by using clean (non-augmented) data, and the output by augmented data. This is analogous to supervised training with data augmentation and expected to facilitate unsupervised clustering too. Finally, we instantiate five DEC-DA based algorithms. Extensive experiments validate that incorporating data augmentation can improve the clustering performance by a large margin. Our DEC-DA algorithms become the new state of the art on various datasets.

Cite this Paper

BibTeX
@InProceedings{pmlr-v95-guo18b, title = {Deep Embedded Clustering with Data Augmentation}, author = {Guo, Xifeng and Zhu, En and Liu, Xinwang and Yin, Jianping}, booktitle = {Proceedings of The 10th Asian Conference on Machine Learning}, pages = {550--565}, year = {2018}, editor = {Zhu, Jun and Takeuchi, Ichiro}, volume = {95}, series = {Proceedings of Machine Learning Research}, month = {14--16 Nov}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v95/guo18b/guo18b.pdf}, url = {https://proceedings.mlr.press/v95/guo18b.html}, abstract = {Deep Embedded Clustering (DEC) surpasses traditional clustering algorithms by jointly performing feature learning and cluster assignment. Although a lot of variants have emerged, they all ignore a crucial ingredient, \emph{data augmentation}, which has been widely employed in supervised deep learning models to improve the generalization. To fill this gap, in this paper, we propose the framework of Deep Embedded Clustering with Data Augmentation (DEC-DA). Specifically, we first train an autoencoder with the augmented data to construct the initial feature space. Then we constrain the embedded features with a clustering loss to further learn clustering-oriented features. The clustering loss is composed of the target (pseudo label) and the actual output of the feature learning model, where the target is computed by using clean (non-augmented) data, and the output by augmented data. This is analogous to supervised training with data augmentation and expected to facilitate unsupervised clustering too. Finally, we instantiate five DEC-DA based algorithms. Extensive experiments validate that incorporating data augmentation can improve the clustering performance by a large margin. Our DEC-DA algorithms become the new state of the art on various datasets.} }
Endnote
%0 Conference Paper %T Deep Embedded Clustering with Data Augmentation %A Xifeng Guo %A En Zhu %A Xinwang Liu %A Jianping Yin %B Proceedings of The 10th Asian Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2018 %E Jun Zhu %E Ichiro Takeuchi %F pmlr-v95-guo18b %I PMLR %P 550--565 %U https://proceedings.mlr.press/v95/guo18b.html %V 95 %X Deep Embedded Clustering (DEC) surpasses traditional clustering algorithms by jointly performing feature learning and cluster assignment. Although a lot of variants have emerged, they all ignore a crucial ingredient, \emph{data augmentation}, which has been widely employed in supervised deep learning models to improve the generalization. To fill this gap, in this paper, we propose the framework of Deep Embedded Clustering with Data Augmentation (DEC-DA). Specifically, we first train an autoencoder with the augmented data to construct the initial feature space. Then we constrain the embedded features with a clustering loss to further learn clustering-oriented features. The clustering loss is composed of the target (pseudo label) and the actual output of the feature learning model, where the target is computed by using clean (non-augmented) data, and the output by augmented data. This is analogous to supervised training with data augmentation and expected to facilitate unsupervised clustering too. Finally, we instantiate five DEC-DA based algorithms. Extensive experiments validate that incorporating data augmentation can improve the clustering performance by a large margin. Our DEC-DA algorithms become the new state of the art on various datasets.
APA
Guo, X., Zhu, E., Liu, X. & Yin, J.. (2018). Deep Embedded Clustering with Data Augmentation. Proceedings of The 10th Asian Conference on Machine Learning, in Proceedings of Machine Learning Research 95:550-565 Available from https://proceedings.mlr.press/v95/guo18b.html.

Related Material