New answers tagged

1 vote

Image segmentation with varying resolution

Usually the solution would be just to add padding, and use a model that is trained to handle padding. In other words, fix a resolution, and then downscale the image you are handling to fit in that ...
Alberto's user avatar
  • 911
0 votes

How to add engineered features to an image segmentation model

Adding distance information before the final 1x1 convolutional layer implies that that distance information can be used to linearly separate the two similar classes, given the similar visual features. ...
Alexander Wan's user avatar

Top 50 recent answers are included