Open Peer Review. Open Publishing. Open Access. Open Discussion. Open Directory. Open Recommendations. Open API. Open Source.
Few-shot Autoregressive Density Estimation: Towards Learning to Learn Distributions
Scott Reed, Yutian Chen, Thomas Paine, Aäron van den Oord, S. M. Ali Eslami, Danilo Rezende, Oriol Vinyals, Nando de Freitas
Feb 15, 2018 (modified: Feb 22, 2018)ICLR 2018 Conference Blind Submissionreaders: everyoneShow Bibtex
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.
TL;DR:Few-shot learning PixelCNN
Keywords:few-shot learning, density models, meta learning
Enter your feedback below and we'll get back to you as soon as possible.