Corpus ID: 8122361

Attend, Infer, Repeat: Fast Scene Understanding with Generative Models

@article{Eslami2016AttendIR,
  title={Attend, Infer, Repeat: Fast Scene Understanding with Generative Models},
  author={S. M. Ali Eslami and Nicolas Manfred Otto Heess and Theophane Weber and Yuval Tassa and David Szepesvari and Koray Kavukcuoglu and Geoffrey E. Hinton},
  journal={ArXiv},
  year={2016},
  volume={abs/1603.08575}
}
  • S. M. Ali Eslami, Nicolas Manfred Otto Heess, +4 authors Geoffrey E. Hinton
  • Published 2016
  • Computer Science
  • ArXiv
  • We present a framework for efficient inference in structured image models that explicitly reason about objects. We achieve this by performing probabilistic inference using a recurrent neural network that attends to scene elements and processes them one at a time. Crucially, the model itself learns to choose the appropriate number of inference steps. We use this scheme to learn to perform inference in partially specified 2D models (variable-sized variational auto-encoders) and fully specified 3D… CONTINUE READING

    Citations

    Publications citing this paper.
    SHOWING 1-10 OF 229 CITATIONS

    Multi-Object Representation Learning with Iterative Variational Inference

    VIEW 2 EXCERPTS
    CITES BACKGROUND

    Sequential Attend, Infer, Repeat: Generative Modelling of Moving Objects

    VIEW 7 EXCERPTS
    CITES BACKGROUND & METHODS
    HIGHLY INFLUENCED

    Investigating Object Compositionality in Generative Adversarial Networks

    VIEW 5 EXCERPTS
    CITES BACKGROUND & RESULTS
    HIGHLY INFLUENCED

    Learning to Exploit Stability for 3D Scene Parsing

    VIEW 1 EXCERPT
    CITES RESULTS

    Unsupervised and interpretable scene discovery with Discrete-Attend-Infer-Repeat

    VIEW 13 EXCERPTS
    CITES BACKGROUND & METHODS
    HIGHLY INFLUENCED

    A Case for Object Compositionality in GANs

    VIEW 2 EXCERPTS
    CITES BACKGROUND & METHODS

    FILTER CITATIONS BY YEAR

    2016
    2020

    CITATION STATISTICS

    • 35 Highly Influenced Citations

    • Averaged 57 Citations per year from 2018 through 2020

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 58 REFERENCES

    Picture: A probabilistic programming language for scene perception

    Auto-Encoding Variational Bayes

    VIEW 5 EXCERPTS
    HIGHLY INFLUENTIAL