Corpus ID: 13936837

Learning Structured Output Representation using Deep Conditional Generative Models

@inproceedings{Sohn2015LearningSO,
  title={Learning Structured Output Representation using Deep Conditional Generative Models},
  author={Kihyuk Sohn and H. Lee and Xinchen Yan},
  booktitle={NIPS},
  year={2015}
}
  • Kihyuk Sohn, H. Lee, Xinchen Yan
  • Published in NIPS 2015
  • Computer Science
  • Supervised deep learning has been successfully applied to many recognition problems. [...] Key Method The model is trained efficiently in the framework of stochastic gradient variational Bayes, and allows for fast prediction using stochastic feed-forward inference. In addition, we provide novel strategies to build robust structured prediction algorithms, such as input noise-injection and multi-scale prediction objective at training. In experiments, we demonstrate the effectiveness of our proposed algorithm in…Expand Abstract
    997 Citations
    Structured Output Learning with Conditional Generative Flows
    • 13
    • PDF
    Deep neural networks regularization for structured output prediction
    • 5
    • PDF
    UNCONDITIONAL GENERATIVE MODELS
    • Highly Influenced
    Deep Generative Models: Deterministic Prediction with an Application in Inverse Rendering
    • PDF
    Learning Generative Models from Incomplete Data
    • 1
    • Highly Influenced
    • PDF
    Multimodal Generative Models for Scalable Weakly-Supervised Learning
    • 61
    • PDF
    Conditional Generative Modeling via Learning the Latent Space
    • 1
    • PDF
    Unsupervised Binary Representation Learning with Deep Variational Networks
    • 12
    • Highly Influenced

    References

    SHOWING 1-10 OF 40 REFERENCES
    Deep Generative Stochastic Networks Trainable by Backprop
    • 314
    • PDF
    Unsupervised learning of hierarchical representations with convolutional deep belief networks
    • 310
    • PDF
    Improved Multimodal Deep Learning with Variation of Information
    • 142
    • PDF
    Auto-Encoding Variational Bayes
    • 10,476
    • Highly Influential
    • PDF
    Learning Stochastic Feedforward Neural Networks
    • 106
    • Highly Influential
    • PDF
    Stochastic Backpropagation and Approximate Inference in Deep Generative Models
    • 2,931
    • Highly Influential
    • PDF
    Exploring Compositional High Order Pattern Potentials for Structured Output Learning
    • 36
    • PDF
    Extracting and composing robust features with denoising autoencoders
    • 4,281
    • PDF
    Semi-supervised Learning with Deep Generative Models
    • 1,583
    • PDF
    Generative Adversarial Nets
    • 20,160
    • PDF