• Computer Science
  • Published in ICML 2018

Image Transformer

@inproceedings{Parmar2018ImageT,
  title={Image Transformer},
  author={Niki Parmar and Ashish Vaswani and Jakob Uszkoreit and Lukasz Kaiser and Noam Shazeer and Alexander Ku and Dustin Tran},
  booktitle={ICML},
  year={2018}
}
Image generation has been successfully cast as an autoregressive sequence generation or transformation problem. Recent work has shown that self-attention is an effective way of modeling textual sequences. In this work, we generalize a recently proposed model architecture based on self-attention, the Transformer, to a sequence modeling formulation of image generation with a tractable likelihood. By restricting the self-attention mechanism to attend to local neighborhoods we significantly… CONTINUE READING

Citations

Publications citing this paper.
SHOWING 1-10 OF 49 CITATIONS

Axial Attention in Multidimensional Transformers

VIEW 6 EXCERPTS
CITES BACKGROUND
HIGHLY INFLUENCED

On Recognizing Texts of Arbitrary Shapes with 2D Self-Attention

VIEW 4 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Auto Completion of User Interface Layout Design Using Transformer-Based Tree Decoders

VIEW 3 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Convolutional Conditional Neural Processes

VIEW 4 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Music Transformer: Generating Music with Long-Term Structure

VIEW 4 EXCERPTS
CITES BACKGROUND & METHODS

RELATIVE PIXEL PREDICTION FOR AUTOREGRESSIVE IMAGE GENERATION

  • 2019
VIEW 6 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

SCRAM: Spatially Coherent Randomized Attention Maps

VIEW 5 EXCERPTS
CITES METHODS, BACKGROUND & RESULTS
HIGHLY INFLUENCED

Adversarial Code Learning for Image Generation

VIEW 1 EXCERPT
CITES BACKGROUND

References

Publications referenced by this paper.
SHOWING 1-10 OF 18 REFERENCES

Attention is All you Need

VIEW 9 EXCERPTS

Pixel Recursive Super Resolution

VIEW 8 EXCERPTS
HIGHLY INFLUENTIAL

PixelSNAIL: An Improved Autoregressive Generative Model

VIEW 8 EXCERPTS
HIGHLY INFLUENTIAL

Conditional Image Generation with PixelCNN Decoders

VIEW 10 EXCERPTS
HIGHLY INFLUENTIAL

Generating Images from Captions with Attention

VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network

VIEW 2 EXCERPTS

URL http://arxiv.org/ abs/1610.00527

  • Kalchbrenner, Nal, +11 authors Koray
  • Video pixel networks. CoRR,
  • 2016
VIEW 1 EXCERPT