Few-shot Autoregressive Density Estimation: Towards Learning to Learn Distributions

by   Scott Reed, et al.

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.


page 3

page 6

page 7

page 8

page 11


Parallel Multiscale Autoregressive Density Estimation

PixelCNN achieves state-of-the-art results in density estimation for nat...

Masked Autoregressive Flow for Density Estimation

Autoregressive models are among the best performing neural density estim...

Understanding the (un)interpretability of natural image distributions using generative models

Probability density estimation is a classical and well studied problem, ...

PixelPyramids: Exact Inference Models from Lossless Image Pyramids

Autoregressive models are a class of exact inference approaches with hig...

Locally Masked Convolution for Autoregressive Models

High-dimensional generative models have many applications including imag...

AdaCat: Adaptive Categorical Discretization for Autoregressive Models

Autoregressive generative models can estimate complex continuous data di...

Gransformer: Transformer-based Graph Generation

Transformers have become widely used in modern models for various tasks ...

Please sign up or login with your details

Forgot password? Click here to reset