Processing images using deep neural networks
Methods, systems, and apparatus, including computer programs encoded on computer storage media, for image processing using deep neural networks. One of the methods includes receiving data characterizing an input image; processing the data characterizing the input image using a deep neural network to generate an alternative representation of the input image, wherein the deep neural network comprises a plurality of subnetworks, wherein the subnetworks are arranged in a sequence from lowest to highest, and wherein processing the data characterizing the input image using the deep neural network comprises processing the data through each of the subnetworks in the sequence; and processing the alternative representation of the input image through an output layer to generate an output from the input image.
1. A system comprising:
a deep neural network configured to process data characterizing an input image to generate an alternative representation of the input image, the deep neural network comprising:
a plurality of subnetworks arranged in a sequence from lowest to highest, the plurality of subnetworks configured to process the data according to the sequence, the plurality of subnetworks comprising a plurality of module subnetworks, each of the module subnetworks comprising:
a pass-through convolutional layer configured to process a preceding output representation generated by a preceding subnetwork in the sequence and generate a pass-through output,
one or more groups of neural network layers configured to process the preceding output representation receive to generate a respective group output for each of the one or more groups, and
a concatenation layer configured to concatenate the pass-through output and the group outputs to generate an output representation for the module subnetwork; and
an output layer configured to process the alternative representation of the input image to generate an output from the input image.
2. The system of claim 1 , wherein the pass-through convolutional layer is a 1×1 convolutional layer.
3. The system of claim 1 , wherein a first group of the one or more groups of neural network layers includes a first convolutional layer followed by a second convolutional layer.
4. The system of claim 3 , wherein the first convolutional layer is a 1×1 convolutional layer.
5. The system of claim 3 , wherein the second convolutional layer is a 3×3 convolutional layer.
6. The system of claim 3 , wherein a second group of the one or more groups of neural network layers includes a third convolutional layer followed by a fourth convolutional layer.
7. The system of claim 6 , wherein the third convolutional layer is a 1×1 convolutional layer.
8. The system of claim 6 , wherein the fourth convolutional layer is a 5×5 convolutional layer.
9. The system of claim 1 , wherein a third group of the one or more groups of neural network layers includes a first max-pooling layer followed by a fifth convolutional layer.
10. The system of claim 9 , wherein the first max-pooling layer is a 3×3 max pooling layer.
11. The system of claim 9 , wherein the fifth convolutional layer is a 1×1 convolutional layer.
12. The system of claim 1 , wherein the plurality of subnetworks comprises one or more additional max-pooling layers.
13. The system of claim 1 , wherein the plurality of subnetworks comprises one or more initial convolutional layers.
14. A system comprising:
a deep neural network configured to process data characterizing an input image to generate an alternative representation of the input image, the deep neural network comprising:
a plurality of subnetworks arranged in a sequence from lowest to highest, the plurality of subnetworks configured to process the data according to the sequence, the plurality of subnetworks comprising a plurality of module subnetworks, each of the module subnetworks comprising:
a pass-through convolutional layer configured to process a preceding output representation generated by a preceding subnetwork in the sequence and generate a pass-through output,
one or more groups of neural network layers configured to process the preceding output representation receive to generate a respective group output for each of the one or more groups, wherein at least one group of the one or more groups of neural network layers includes a 1×1 convolutional layer followed by a 3×3 convolutional layer, and
a concatenation layer configured to concatenate the pass-through output and the group outputs to generate an output representation for the module subnetwork; and
an output layer configured to process the alternative representation of the input image to generate an output from the input image.
15. The system of claim 14 , wherein the pass-through convolutional layer is a 1×1 convolutional layer.
16. The system of claim 14 , wherein the plurality of subnetworks comprises one or more additional max-pooling layers.
17. The system of claim 14 , wherein the plurality of subnetworks comprises one or more initial convolutional layers.
18. A system comprising:
a deep neural network configured to process data characterizing an input image to generate an alternative representation of the input image, the deep neural network comprising:
a plurality of subnetworks arranged in a sequence from lowest to highest, the plurality of subnetworks configured to process the data according to the sequence, the plurality of subnetworks comprising a plurality of module subnetworks, each of the module subnetworks comprising:
a pass-through convolutional layer configured to process a preceding output representation generated by a preceding subnetwork in the sequence and generate a pass-through output,
a plurality of groups of neural network layers configured to process the preceding output representation receive to generate a respective group output for each of the one or more groups, wherein a first group of the plurality of groups of neural network layers includes a 1×1 convolutional layer followed by a 3×3 convolutional layer, a second group of the plurality of groups of neural network layers includes a 1×1 convolutional layer followed by a 5×5 convolutional layer, and a third group of the plurality of groups of neural network layers includes a 3×3 max pooling layer followed by a 1×1 convolutional layer,
a concatenation layer configured to concatenate the pass-through output and the group outputs to generate an output representation for the module subnetwork; and
an output layer configured to process the alternative representation of the input image to generate an output from the input image.
19. The system of claim 18 , wherein the plurality of subnetworks comprises one or more additional max-pooling layers.
20. The system of claim 18 , wherein the plurality of subnetworks comprises one or more initial convolutional layers.