DRAW: A Recurrent Neural Network For Image Generation

Abstract

This paper introduces the Deep Recurrent Atten-tive 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 distin-guished from real data with the naked eye. 1.

Keywords

MNIST databaseComputer scienceArtificial intelligenceEncoding (memory)Recurrent neural networkImage (mathematics)Artificial neural networkComputer visionGenerative grammarPattern recognition (psychology)

Affiliated Institutions

Related Publications

Image Style Transfer Using Convolutional Neural Networks

Leon A. Gatys , Alexander S. Ecker , Matthias Bethge

Rendering the semantic content of an image in different styles is a difficult image processing task. Arguably, a major limiting factor for previous approaches has been the lack ...

2016 5772 citations

Understanding deep image representations by inverting them

Aravindh Mahendran , Andrea Vedaldi

Image representations, from SIFT and Bag of Visual Words to Convolutional Neural Networks (CNNs), are a crucial component of almost any image understanding system. Nevertheless,...

2015 1831 citations

A survey on Image Data Augmentation for Deep Learning

Connor Shorten , Taghi M. Khoshgoftaar

Abstract Deep convolutional neural networks have performed remarkably well on many Computer Vision tasks. However, these networks are heavily reliant on big data to avoid overfi...

2019 Journal Of Big Data 11041 citations

A Fast Learning Algorithm for Deep Belief Nets

Geoffrey E. Hinton , Simon Osindero , Yee‐Whye Teh

We show how to use “complementary priors” to eliminate the explaining-away effects that make inference difficult in densely connected belief nets that have many hidden layers. U...

2006 Neural Computation 16027 citations

High-Resolution Image Synthesis with Latent Diffusion Models

Robin Rombach , Andreas Blattmann , Dominik Lorenz +2 more

By decomposing the image formation process into a sequential application of denoising autoencoders, diffusion models (DMs) achieve state-of-the-art synthesis results on image da...

2022 2022 IEEE/CVF Conference on Computer ... 10716 citations

Publication Info

Year: 2015
Type: article
Pages: 1462-1471
Citations: 758
Access: Closed

External Links

Citation Metrics

758

OpenAlex

Cite This

APA Style

                            
                                    Karol Gregor, 
                                
                                    Ivo Danihelka, 
                                
                                    Alex Graves
                                
                                et al.
                            
                            (2015). 
                            DRAW: A Recurrent Neural Network For Image Generation. 
                            
                            , 1462-1471.