Double cycle-consistent generative adversarial network for unsupervised conditional generation
arXiv:1911.05210
Abstract
Conditional generative models have achieved considerable success in the past few years, but usually require a lot of labeled data. Recently, ClusterGAN combines GAN with an encoder to achieve remarkable clustering performance via unsupervised conditional generation. However, it ignores the real conditional distribution of data, which leads to generating less diverse samples for each class and makes the encoder only achieve sub-optimal clustering performance. Here, we propose a new unsupervised conditional generation framework, Double Cycle-Consistent Conditional GAN (DC3-GAN), which can generate diverse class-conditioned samples. We enforce the encoder and the generator of GAN to form an encoder-generator pair in addition to the generator-encoder pair, which enables us to avoid the low-diversity generation and the triviality of latent features. We train the encoder-generator pair using real data, which can indirectly estimate the real conditional distribution. Meanwhile, this framework enforces the outputs of the encoder to match the inputs of GAN and the prior noise distribution, which disentangles latent space into two parts: one-hot discrete and continuous latent variables. The former can be directly expressed as clusters and the latter represents remaining unspecified factors. This work demonstrates that enhancing the diversity of unsupervised conditional generated samples can improve the clustering performance. Experiments on different benchmark datasets show that the proposed method outperforms existing generative model-based clustering methods, and also achieves the optimal disentanglement performance.
12 pages, 4 figures, and 12 tables
References in corpus (26)
- Conditional Generative Adversarial Nets
- A Simple Framework for Contrastive Learning of Visual Representations
- Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
- Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
- GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
- Conditional Image Synthesis With Auxiliary Classifier GANs
- Adversarial Feature Learning
- Disentangling by Factorising
- Adversarially Learned Inference
- Autoencoding beyond pixels using a learned similarity metric
- Towards K-means-friendly Spaces: Simultaneous Deep Learning and Clustering
- Deep Unsupervised Clustering with Gaussian Mixture Variational Autoencoders
- Generative Moment Matching Networks
- Recent Advances in Autoencoder-Based Representation Learning
- Learning Discrete Representations via Information Maximizing Self-Augmented Training
- Disentangling factors of variation in deep representations using adversarial training
- Wasserstein Auto-Encoders
- SpectralNet: Spectral Clustering using Deep Neural Networks
- From Variational to Deterministic Autoencoders
- Self-labelling via simultaneous clustering and representation learning
- High-Fidelity Image Generation With Fewer Labels
- Learning Disentangled Joint Continuous and Discrete Representations
- On gradient regularizers for MMD GANs
- InfoGAN-CR and ModelCentrality: Self-supervised Model Training and Selection for Disentangling GANs
- Dominant Set Clustering and Pooling for Multi-View 3D Object Recognition
- Graph Degree Linkage: Agglomerative Clustering on a Directed Graph