GAN-Based Enhanced Deep Subspace Clustering Networks

Zhiwen Yu, Zhongfan Zhang, Wenming Cao, Cheng Liu, C. L. Philip Chen, Hau-San WongIEEE TKDE 2022 · OpenReview

Abstract

In this paper, we propose two GAN-based deep subspace clustering approaches: deep subspace clustering via dual adversarial generative networks (DSC-DAG) and self-supervised deep subspace clustering with adversarial generative networks (S <inline-formula><tex-math notation="LaTeX">$^2$</tex-math></inline-formula> DSC-AG). In DSC-DAG, the distributions of both the inputs and corresponding latent representations are learnt via adversarial training simultaneously. Besides, there are two kinds of synthetic representations to facilitate the fine-tuning of the encoder: the combinations of latent representations with random combination coefficients and representations of real-like inputs derived from noise variables. In S <inline-formula><tex-math notation="LaTeX">$^2$</tex-math></inline-formula> DSC-AG, a self-supervised information learning module substitutes for adversarial learning in the latent space, since both of them play the same role in learning discriminative latent representations. We analyze connections between these methods and demonstrate their equivalences. We conduct extensive experiments on multiple real-world data sets against state-of-the-art subspace clustering methods in terms of accuracy, normalized mutual information and purity. Experimental results demonstrate the effectiveness and superiority of our proposed methods.
BibTeX
@article{yu2022gan,
  author = {Zhiwen Yu and Zhongfan Zhang and Wenming Cao and Cheng Liu and C. L. Philip Chen and Hau-San Wong},
  title = {{GAN-Based Enhanced Deep Subspace Clustering Networks}},
  journal = {IEEE Trans. Knowl. Data Eng.},
  year = {2022},
  url = {https://openreview.net/forum?id=d1UA3meCms},
}

Loading related content...

Figure