Image classification neural networks

Patent metadata

Field	Value
Publication number	US-11062181-B2
Application number	US-201916550731-A
Country	US
Kind code	B2
Filing date	Aug 26, 2019
Priority date	Feb 18, 2016
Publication date	Jul 13, 2021
Grant date	Jul 13, 2021

Abstract

A neural network system that includes: multiple subnetworks that includes: a first subnetwork including multiple first modules, each first module including: a pass-through convolutional layer configured to process the subnetwork input for the first subnetwork to generate a pass-through output; an average pooling stack of neural network layers that collectively processes the subnetwork input for the first subnetwork to generate an average pooling output; a first stack of convolutional neural network layers configured to collectively process the subnetwork input for the first subnetwork to generate a first stack output; a second stack of convolutional neural network layers that are configured to collectively process the subnetwork input for the first subnetwork to generate a second stack output; and a concatenation layer configured to concatenate the pass-through output, the average pooling output, the first stack output, and the second stack output to generate a first module output for the first module.

First claim

What is claimed is:

1. A neural network system implemented by one or more computers, wherein the neural network system is configured to receive an image and to generate a classification output for the input image, and wherein the neural network system comprises:
a plurality of subnetworks arranged in a stack on top of each other, wherein each subnetwork is configured to process a subnetwork input to generate a subnetwork output and to provide the subnetwork output as input to another subnetwork above the subnetwork in the stack, and wherein the plurality of subnetworks includes:
a first subnetwork comprising a plurality of first modules, each first module comprising:
a first pass-through convolutional layer configured to process the subnetwork input for the first subnetwork to generate a first pass-through output;
a first average pooling stack of neural network layers, wherein the layers in the first average pooling stack are configured to collectively process the subnetwork input for the first subnetwork to generate a first average pooling output;
a first stack of convolutional neural network layers, wherein the layers in the first stack are configured to collectively process the subnetwork input for the first subnetwork to generate a first stack output;
a second stack of convolutional neural network layers, wherein the second stack comprises a 1×1 convolutional layer immediately followed by a 3×3 convolutional layer immediately followed by a 3×3 convolutional layer, and wherein the layers in the second stack are configured to collectively process the subnetwork input for the first subnetwork to generate a second stack output; and
a first concatenation layer configured to concatenate the first pass-through output, the first average pooling output, the first stack output, and the second stack output to generate a first module output for the first module; and

a third subnetwork comprising a plurality of third modules, each third module comprising:
a third pass-through convolutional layer configured to process the subnetwork input for the third subnetwork to generate a third pass-through output;
an third average pooling stack of neural network layers, wherein the layers in the third average pooling stack are configured to collectively process the subnetwork input for the third subnetwork to generate an third average pooling output;
a first group of convolutional neural network layers, wherein the first group including a 1×1 convolutional layer, a 1×3 convolutional layer, and a 3×1 convolutional layer, wherein the layers in the first group are configured to collectively process the subnetwork input for the third subnetwork to generate a first group output;
a second group of convolutional neural network layers, wherein the layers in the second group are configured to collectively process the subnetwork input for the third subnetwork to generate a second group output; and
a third concatenation layer configured to concatenate the pass-through output, the average pooling output, the first group output, and the second group output to generate a third module output for the third module.

2. The neural network system of claim 1 , wherein the first subnetwork includes four first modules.

3. The neural network system of claim 1 , wherein the third subnetwork includes three third modules.

4. The neural network system of claim 1 , wherein at least one of the first pass-through convolutional layer or the third pass-through convolutional layer is a 1×1 convolutional layer.

5. The neural network system of claim 1 , wherein the first average pooling stack includes an average pooling layer followed by a 1×1 convolutional layer.

6. The neural network system of claim 1 , wherein the first stack includes a 1×1 convolutional layer followed by a 3×3 convolutional layer.

7. The neural network system of claim 1 , wherein the first subnetwork is configured to combine the first module outputs generated by the plurality of first subnetworks to generate a first subnetwork output for the first subnetwork.

8. The neural network system of claim 1 , wherein the first subnetwork receives an input that is 35×35 ×384 and each first module generates an output that is 35×35 ×384.

9. The neural network system of claim 1 , wherein the third average pooling stack includes an average pooling layer followed by a 1×1 convolutional layer.

10. The neural network system of claim 1 , wherein:
the 1×1 convolutional layer in the first group is configured to process the subnetwork input for the third subnetwork to generate a first intermediate output;
the 1×3 convolutional layer in the first group is configured to process the first intermediate output to generate a second intermediate output;
the 3×1 convolutional layer in the first group is configured to process the first intermediate output to generate a third intermediate output; and
wherein the first group further includes a first group concatenation layer configured to concatenate the second intermediate output and the third intermediate output to generate the first group output.

11. The neural network system of claim 1 , wherein the second group includes:
a fifth stack of convolutional layers that is configured to process the subnetwork input for the third subnetwork to generate a fifth stack output;
a 1×3 convolutional layer configured to process the fifth stack output to generate a fourth intermediate output;
a 3×1 convolutional layer configured to process the fifth stack output to generate a fifth intermediate output; and
a second group concatenation layer configured to concatenate the fourth intermediate output and the fifth intermediate output to generate the second group output.

12. The neural network system of claim 6 , wherein the fifth stack includes a 1×1 convolutional layer followed by a 1×3 convolutional layer followed by a 3×1 convolutional layer.

13. The neural network system of claim 1 , wherein the third subnetwork is configured to combine the third module outputs generated by the plurality of third modules to generate a third subnetwork output for the third subnetwork.

14. The neural network system of claim 1 , wherein the third subnetwork receives an input that is 8×8 ×1536 and each third module generates an output that is 8×8 ×1536.

15. One or more non-transitory storage media encoded with instructions that when executed by one or more computers cause the one or more computers to implement a neural network system that is configured to receive an image and to generate a classification output for the input image, wherein the neural network system comprises:
a plurality of subnetworks arranged in a stack on top of each other, wherein each subnetwork is configured to process a subnetwork input to generate a subnetwork output and to provide the subnetwork output as input to another subnetwork above the subnetwork in the stack, and wherein the plurality of subnetworks includes:
a first subnetwork comprising a plurality of first modules, each first module comprising:
a first pass-through convolutional layer configured to process the subnetwork input for the first subnetwork to generate a first pass-through output;
a first average pooling stack of neural network layers, wherein the layers in the first average pooling stack are configured to collectively process the subnetwork input for the first subnetwork to generate a first average pooling output;
a first stack of convolutional neural network layers, wherein the layers in the first stack are configured to collectively process the subnetwork input for the first subnetwork to generate a first stack output;
a second stack of co

Assignees

• Google Llc

Inventors

• Vanhoucke Vincent O
• Szegedy Christian
• Ioffe Sergey

Classifications

• G06F18/24

  Classification techniques · CPC title

• G06V10/454 Primary

  Integrating the filters into a hierarchical structure, e.g. convolutional neural networks [CNN] · CPC title

• G06N3/048

  Activation functions · CPC title

• G06N3/045 Primary

  Combinations of networks · CPC title

• G06N3/044

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