Few-shot Autoregressive Density Estimation: Towards Learning to Learn Distributions
Abstract
Deep autoregressive models have shown state-of-the-art performance in density estimation for natural images on large-scale datasets such as ImageNet. However, such models require many thousands of gradient-based weight updates and unique image examples for training. Ideally, the models would rapidly learn visual concepts from only a handful of examples, similar to the manner in which humans learns across many vision tasks. In this paper, we show how 1) neural attention and 2) meta learning techniques can be used in combination with autoregressive models to enable effective few-shot density estimation. Our proposed modifications to PixelCNN result in state-of-the art few-shot density estimation on the Omniglot dataset. Furthermore, we visualize the learned attention policy and find that it learns intuitive algorithms for simple tasks such as image mirroring on ImageNet and handwriting on Omniglot without supervision. Finally, we extend the model to natural images and demonstrate few-shot image generation on the Stanford Online Products dataset.
Cite
@article{arxiv.1710.10304,
title = {Few-shot Autoregressive Density Estimation: Towards Learning to Learn Distributions},
author = {Scott Reed and Yutian Chen and Thomas Paine and Aäron van den Oord and S. M. Ali Eslami and Danilo Rezende and Oriol Vinyals and Nando de Freitas},
journal= {arXiv preprint arXiv:1710.10304},
year = {2018}
}