ClusterGAN : Latent Space Clustering in Generative Adversarial Networks

@article{Mukherjee2019ClusterGANL,
  title={ClusterGAN : Latent Space Clustering in Generative Adversarial Networks},
  author={S. Mukherjee and Himanshu Asnani and Eugene Lin and S. Kannan},
  journal={ArXiv},
  year={2019},
  volume={abs/1809.03627}
}
Generative Adversarial networks (GANs) have obtained remarkable success in many unsupervised learning tasks and unarguably, clustering is an important unsupervised learning problem. [...] Key Method By sampling latent variables from a mixture of one-hot encoded variables and continuous latent variables, coupled with an inverse network (which projects the data to the latent space) trained jointly with a clustering specific loss, we are able to achieve clustering in the latent space. Our results show a remarkable…Expand
90 Citations
Effect of the Latent Structure on Clustering With GANs
  • 2
  • Highly Influenced
  • PDF
CPGAN: Curve Clustering Architecture Based on Projected Latent Vector of Generative Adversarial Network
  • Highly Influenced
  • PDF
Learning Robust Representation for Clustering through Locality Preserving Variational Discriminative Network
  • Highly Influenced
  • PDF
Latent Space Growing of Generative Adversarial Networks
Speaker Diarization Using Latent Space Clustering in Generative Adversarial Network
  • 8
  • Highly Influenced
  • PDF
Clustering by Directly Disentangling Latent Space
  • 2
  • Highly Influenced
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 30 REFERENCES
Inverting the Generator of a Generative Adversarial Network
  • 110
  • PDF
Adversarial Feature Learning
  • 1,048
  • PDF
Towards K-means-friendly Spaces: Simultaneous Deep Learning and Clustering
  • 289
  • PDF
Adversarially Learned Inference
  • 888
  • PDF
Deep Subspace Clustering Networks
  • 179
  • PDF
Precise Recovery of Latent Vectors from Generative Adversarial Networks
  • 111
  • PDF
Improved Training of Wasserstein GANs
  • 4,074
  • PDF
Generative Adversarial Nets
  • 21,507
  • PDF
InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets
  • 2,372
  • PDF
Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
  • 7,590
  • PDF
...
1
2
3
...