System and method for semantic segmentation using dense upsampling convolution (DUC)
First Claim
Patent Images
1. A system comprising:
- a data processor; and
an image processing module, executable by the data processor, the image processing module being configured to perform semantic segmentation using a dense upsampling convolution (DUC) operation, the DUC operation being configured to;
receive an input image;
produce a feature map from the input image;
perform a convolution operation on the feature map and reshape the feature map to produce a label map;
divide the label map into equal subparts, which have the same height and width as the feature map;
stack the subparts of the label map to produce a whole label map; and
apply a convolution operation directly between the feature map and the whole label map without inserting extra values in deconvolutional layers to produce a semantic label map.
2 Assignments
0 Petitions
Accused Products
Abstract
A system and method for semantic segmentation using dense upsampling convolution (DUC) are disclosed. A particular embodiment includes: receiving an input image; producing a feature map from the input image; performing a convolution operation on the feature map and reshape the feature map to produce a label map; dividing the label map into equal subparts, which have the same height and width as the feature map; stacking the subparts of the label map to produce a whole label map; and applying a convolution operation directly between the feature map and the whole label map without inserting extra values in deconvolutional layers to produce a semantic label map.
-
Citations
18 Claims
-
1. A system comprising:
-
a data processor; and an image processing module, executable by the data processor, the image processing module being configured to perform semantic segmentation using a dense upsampling convolution (DUC) operation, the DUC operation being configured to; receive an input image; produce a feature map from the input image; perform a convolution operation on the feature map and reshape the feature map to produce a label map; divide the label map into equal subparts, which have the same height and width as the feature map; stack the subparts of the label map to produce a whole label map; and apply a convolution operation directly between the feature map and the whole label map without inserting extra values in deconvolutional layers to produce a semantic label map. - View Dependent Claims (2, 3, 4, 5, 6)
-
-
7. A method comprising:
-
receiving an input image; producing a feature map from the input image; performing a convolution operation on the feature map and reshaping the feature map to produce a label map; dividing the label map into equal subparts, which have the same height and width as the feature map; stacking the subparts of the label map to produce a whole label map; and applying a convolution operation directly between the feature map and the whole label map without inserting extra values in deconvolutional layers to produce a semantic label map. - View Dependent Claims (8, 9, 10, 11, 12)
-
-
13. A non-transitory machine-useable storage medium embodying instructions which, when executed by a machine, cause the machine to:
-
receive an input image; produce a feature map from the input image; perform a convolution operation on the feature map and reshape the feature map to produce a label map; divide the label map into equal subparts, which have the same height and width as the feature map; stack the subparts of the label map to produce a whole label map; and apply a convolution operation directly between the feature map and the whole label map without inserting extra values in deconvolutional layers to produce a semantic label map. - View Dependent Claims (14, 15, 16, 17, 18)
-
Specification