US 11,922,291 B2
Image processing via isotonic convolutional neural networks
Asher Trockman, Stuttgart (DE); Jeremy Kolter, Pittsburgh, PA (US); Devin T. Willmott, Pittsburgh, PA (US); and Filipe J. Cabrita Condessa, Pittsburgh, PA (US)
Assigned to Robert Bosch GmbH, (DE); and Carnegie Mellon University
Filed by Robert Bosch GmbH, Stuttgart (DE); and Carnegie Mellon University, Pittsburgh, PA (US)
Filed on Sep. 28, 2021, as Appl. No. 17/487,631.
Prior Publication US 2023/0096021 A1, Mar. 30, 2023
Int. Cl. G06T 7/00 (2017.01); G06F 18/2431 (2023.01); G06N 3/047 (2023.01); G06T 7/11 (2017.01)
CPC G06N 3/047 (2023.01) [G06F 18/2431 (2023.01); G06T 7/11 (2017.01); G06T 2207/10044 (2013.01); G06T 2207/10132 (2013.01); G06T 2207/20021 (2013.01); G06T 2207/20084 (2013.01)] 19 Claims
OG exemplary drawing
 
1. A computer-implemented method for processing an image utilizing a convolutional neural network, the computer-implemented method comprising:
receiving an image;
dividing the image into patches, each patch of size p;
extracting, via a first convolutional layer, a feature map having a number of channels based on a feature detector of size p, wherein the feature detector has a stride equal to size p;
refining the feature map by alternatingly applying depth-wise convolutional layers and point-wise convolutional layers to obtain a refined feature map, wherein the number of channels in the feature map, and the size of the feature map remains constant throughout all operations in the refinement; and
outputting the refined feature map.