Corpus ID: 182952301

Multi-objects Generation with Amortized Structural Regularization

@article{Xu2019MultiobjectsGW,
  title={Multi-objects Generation with Amortized Structural Regularization},
  author={Kun Xu and Chongxuan Li and Jun Zhu and B. Zhang},
  journal={ArXiv},
  year={2019},
  volume={abs/1906.03923}
}
Deep generative models (DGMs) have shown promise in image generation. [...] Key Method In this paper, we propose the amortized structural regularization (ASR) framework, which adopts the posterior regularization (PR) to embed human knowledge into DGMs via a set of structural constraints. We derive a lower bound of the regularized log-likelihood, which can be jointly optimized with respect to the generative model and recognition model efficiently. Empirical results show that ASR significantly outperforms the DGM…Expand
4 Citations

References

SHOWING 1-10 OF 32 REFERENCES
Deep Structured Generative Models
  • 5
  • PDF
Multi-Object Representation Learning with Iterative Variational Inference
  • 118
  • Highly Influential
  • PDF
Deep Generative Models with Learnable Knowledge Constraints
  • 43
  • PDF
Attend, Infer, Repeat: Fast Scene Understanding with Generative Models
  • 277
  • Highly Influential
  • PDF
beta-VAE: Learning Basic Visual Concepts with a Constrained Variational Framework
  • 1,723
Amortized Inference Regularization
  • 11
  • PDF
Max-Margin Deep Generative Models
  • 28
  • PDF
Deep Unsupervised Clustering with Gaussian Mixture Variational Autoencoders
  • 290
  • PDF
Generative Adversarial Nets
  • 21,551
  • PDF
Auto-Encoding Variational Bayes
  • 11,340
  • Highly Influential
  • PDF
...
1
2
3
4
...