End to end network model for high resolution image segmentation

A computer-implemented method of generating a segmentation mask for at least a part of an image, comprising:

• receiving, at a first neural network, first data derived from the image,
• processing said first data, using the first neural network, to generate an output of the first neural network, wherein said output relates to a first segmentation mask, the first semantic segmentation mask comprising the image partitioned into plurality of segments, the first semantic segmentation mask indicative of a boundary of an object;
• receiving, at a second neural network:
• second data derived from the image, and
• data derived from said output of the first neural network;
• and
• generating data relating to a second segmentation mask, comprising processing, using the second neural network, the second data derived from the image and the data derived from said output of the first neural network, such that the second segmentation mask is refined with respect to the first segmentation mask.

A computer-implemented method of training an image segmentation model from end to end, the image segmentation model comprising a semantic segmentation neural network and an edge refinement neural network, the method comprising:

• inputting a training image into the image segmentation model;
• determining a first loss function for the semantic segmentation neural network;
• determining a second loss function for the edge refinement neural network;
• determining a total loss function based at least in part on the first loss function and second loss function;
• and
• training the image segmentation model based on the total loss function;
• wherein the semantic segmentation neural network is trained to receive an image and, in response to receipt of the image, output a semantic segmentation mask, the semantic segmentation mask indicative of a boundary of an object, and
• wherein the edge refinement neural network is trained to receive at least a portion of the image and at least a portion of the semantic segmentation mask and, in response to receipt of the at least a portion of the image and at least a portion of the semantic segmentation mask, output a refined semantic segmentation mask.