HackerPapers

arXiv:1502.04623cs.CV

DRAW: A Recurrent Neural Network For Image Generation

Karol Gregor, Ivo Danihelka, Alex Graves, Danilo Jimenez Rezende, Daan Wierstra

Abstract

This paper introduces the Deep Recurrent Attentive Writer (DRAW) neural network architecture for image generation. DRAW networks combine a novel spatial attention mechanism that mimics the foveation of the human eye, with a sequential variational auto-encoding framework that allows for the iterative construction of complex images. The system substantially improves on the state of the art for generative models on MNIST, and, when trained on the Street View House Numbers dataset, it generates images that cannot be distinguished from real data with the naked eye.

arXiv comments
Journal reference
DOI
Subjects
cs.CVComputer Vision and Pattern Recognition cs.LGMachine Learning cs.NENeural and Evolutionary Computing

On Hacker News

Linked by 3 identifiable commenters in 3 comments across 3 threads, from Sep 2015 to Feb 2020. Found in 2 HN submissions from Feb 2015 to Feb 2015. Open submission discussions.

Comments linking this paper, per year.

Discussed in comments3 threads

  1. JPEG Committee releases a call for evidence for image compression based on AI 1 comment

    • > But much more interesting to me is a lossless domain-specific compressor, which I’m not aware of any examples of. (Please tell me if about some if you know them!) A bit academic, but if you check out this paper from 2015 https://arxiv.org/pdf/1502.04623.pdf on a neural network…

      0-_-0View on HNParent context

  2. Image Compression with Neural Networks 1 comment

    • Expecting 2 years of research by around 20 of the best DNN researchers on the planet to be compressed into a StackOverflow answer before it has been done seems a fairly large amount to expect. Not a huge fan of the negativity on StackOverflow, but until August 2016 (when the…

      nlView on HNParent context

  3. Towards universal neural nets: Gibbs machines and ACE 1 comment

    • Guy, the only thing abundantly clear is that you are full of dung. Your shameless self-promotion may piss-off the police chief here - murbard2, so be more careful. Ten digits better classified, out of 10000? With a structure more complicated than a human DNA vs two lines of…

      themann9View on HNParent context

Submitted to Hacker News

Connected through shared HN threads, not inferred similarity or a recommendation.