US 10,762,425 B2 · Learning affinity via a spatial propagation neural network

Abstract

A spatial linear propagation network (SLPN) system learns the affinity matrix for vision tasks. An affinity matrix is a generic matrix that defines the similarity of two points in space. The SLPN system is trained for a particular computer vision task and refines an input map (i.e., affinity matrix) that indicates pixels the share a particular property (e.g., color, object, texture, shape, etc.). Inputs to the SLPN system are input data (e.g., pixel values for an image) and the input map corresponding to the input data to be propagated. The input data is processed to produce task-specific affinity values (guidance data). The task-specific affinity values are applied to values in the input map, with at least two weighted values from each column contributing to a value in the refined map data for the adjacent column.

Claims20

Dependent claims

A computer-implemented method, comprising:

receiving an input map defining properties of pixels in an image;
receiving task-specific affinity values for the pixels in the image;
and
processing, by a spatial linear propagation module, the input map and the task-specific affinity values to produce refined map data, wherein at least two task-specific affinity values aligned in a first pixel dimension are applied to spatially corresponding values in the input map to generate each refined value of the refined map data.

1 more element

Dependencies are inferred from the claim text.

Learning affinity via a spatial propagation neural network

Life of this patent

Learning affinity via a spatial propagation neural network

Life of this patent

Abstract

Claims20