Compressing images using neural networks

Patent metadata

Field	Value
Publication number	US-10432953-B2
Application number	US-201615396332-A
Country	US
Kind code	B2
Filing date	Dec 30, 2016
Priority date	Feb 5, 2016
Publication date	Oct 1, 2019
Grant date	Oct 1, 2019

Abstract

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for compressing images using neural networks. One of the methods includes receiving an image; processing the image using an encoder neural network, wherein the encoder neural network is configured to receive the image and to process the image to generate an output defining values of a first number of latent variables that each represent a feature of the image; generating a compressed representation of the image using the output defining the values of the first number of latent variables; and providing the compressed representation of the image for use in generating a reconstruction of the image.

First claim

What is claimed is:

1. A method comprising:
receiving an image;
processing the image using an encoder neural network, wherein the encoder neural network is configured to receive the image and to process the image to generate an output defining values of latent variables that each represent a feature of the image;
generating a lossy compressed representation of the image using a first number of the latent variables that is less than all of the latent variables that have values that are defined by the output;
providing the lossy compressed representation of the image for use in generating a reconstruction of the image; and
generating the reconstruction of the image from the lossy compressed representation of the image, comprising:
selecting a value of the latent variables that are not in the first number of latent variables randomly from a prior distribution; and
generating the reconstruction of the image by conditioning a generative neural network on the values of the first number of latent variables and the randomly selected values of the latent variables that are not in the first number of latent variables.

2. The method of claim 1 , wherein generating the lossy compressed representation of the image comprises:
discretizing the values of the first number of latent variables; and
compressing a sequence of the discretized values using arithmetic encoding.

3. The method of claim 2 , further comprising:
determining a respective probability for each of the first number of latent variables by sampling from a prior distribution parameterized by a hidden state of a generative neural network, wherein compressing the sequence of the discretized values comprises:
compressing the sequence of the discretized values and their respective probabilities using arithmetic encoding.

4. The method of claim 1 , wherein, for each latent variable, the output parametrizes a distribution from which the value of the latent variable is selected.

5. The method of claim 1 , wherein the encoder neural network comprises a plurality of neural network layers, and wherein each of the plurality of neural network layers is configured to generate a respective layer output defining a value of a respective latent variable that represents a feature of the image.

6. The method of claim 5 , wherein the latent variables in the first number of latent variables are less than all of the latent variables that have values that are defined by the layer outputs of the plurality of neural network layers.

7. The method of claim 6 , wherein the plurality of neural network layers are arranged in a hierarchy, and wherein the first number of latent variables are the latent variables that have values that are defined by the layer outputs of a predetermined number of highest levels in the hierarchy.

8. The method of claim 1 , wherein the features that are arranged in a hierarchy from least abstract representation of the image to most abstract representation of the image, and wherein the first number of latent variables are the latent variables that represent features at a predetermined number of highest levels in the hierarchy.

9. The method of claim 1 , wherein the generative neural network and the encoder neural network have been jointly trained as a variational auto-encoder.

10. The method of claim 1 , wherein the generative neural network and the encoder neural network are recurrent neural networks.

11. The method of claim 1 , wherein providing the lossy compressed representation comprises transmitting the lossy compressed representation over a data communication network to a decoder system.

12. The method of claim 1 , wherein providing the lossy compressed representation comprises storing the lossy compressed representation in a memory and, in response to a request to retrieve the image from the memory, retrieving the lossy compressed representation from the memory and providing the lossy compressed representation for use in reconstructing the image.

13. A system comprising one or more computers and one or more storage devices storing instructions that when executed by the one or more computers cause the one or more computers to perform operations comprising:
receiving an image;
processing the image using an encoder neural network, wherein the encoder neural network is configured to receive the image and to process the image to generate an output defining values of latent variables that each represent a feature of the image;
generating a lossy compressed representation of the image using a first number of the latent variables that is less than all of the latent variables that have values that are defined by the output;
providing the lossy compressed representation of the image for use in generating a reconstruction of the image; and
generating the reconstruction of the image from the lossy compressed representation of the image, comprising:
selecting a value of the latent variables that are not in the first number of latent variables randomly from a prior distribution; and
generating the reconstruction of the image by conditioning a generative neural network on the values of the first number of latent variables and the randomly selected values of the latent variables that are not in the first number of latent variables.

14. The system of claim 13 , wherein generating the lossy compressed representation of the image comprises:
discretizing the values of the first number of latent variables; and
compressing a sequence of the discretized values using arithmetic encoding.

15. The system of claim 14 , the operations further comprising:
determining a respective probability for each of the first number of latent variables by sampling from a prior distribution parameterized by a hidden state of a generative neural network, wherein compressing the sequence of the discretized values comprises:
compressing the sequence of the discretized values and their respective probabilities using arithmetic encoding.

16. The system of claim 13 , wherein the features that are arranged in a hierarchy from least abstract representation of the image to most abstract representation of the image, and wherein the first number of latent variables are the latent variables that represent features at a predetermined number of highest levels in the hierarchy.

17. The system of claim 13 , wherein the generative neural network and the encoder neural network have been jointly trained as a variational auto-encoder.

18. One or more non-transitory computer storage media storing instructions that when executed by one or more computers cause the one or more computers to perform operations comprising:
receiving an image;
processing the image using an encoder neural network, wherein the encoder neural network is configured to receive the image and to process the image to generate an output defining values of latent variables that each represent a feature of the image;
generating a lossy compressed representation of the image using a first number of the latent variables that is less than all of the latent variables that have values that are defined by the output;
providing the lossy compressed representation of the image for use in generating a reconstruction of the image; and
generating the reconstruction of the image from the lossy compressed representation of the image, comprising:
selecting a value of the latent variables that are not in the first number of latent variables randomly from a prior distribution; and
generating the reconstruction of the image by conditioning a generative neural network on the values of t

Assignees

• Deepmind Tech Ltd

Inventors

• Wierstra Daniel Pieter
• Gregor Karol
• Besse Frederic Olivier

Classifications

• G06N3/047

  Probabilistic or stochastic networks · CPC title

• G06N3/044

  Recurrent networks, e.g. Hopfield networks · CPC title

• G06N3/045

  Combinations of networks · CPC title

• G06T9/002 Primary

  using neural networks · CPC title

• H04N19/30 Primary

  using hierarchical techniques, e.g. scalability (H04N19/63 takes precedence) · CPC title