DRAW: A Recurrent Neural Network For Image Generation
This work addresses the problem of generating high-quality images for machine learning applications, representing a novel approach rather than an incremental improvement.
The paper tackles image generation by introducing the Deep Recurrent Attentive Writer (DRAW) neural network, which combines spatial attention and sequential variational auto-encoding to iteratively construct images, achieving state-of-the-art results on MNIST and generating realistic images on the Street View House Numbers dataset.
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.