Non-uniform image sampling for better image segmentation

Non-uniform image sampling for better image segmentation

Learning to Downsample for Segmentation of Ultra-High Resolution Images
arXiv paper abstract https://arxiv.org/abs/2109.11071v1
arXiv PDF paper https://arxiv.org/pdf/2109.11071v1.pdf

Segmentation of ultra-high resolution images with deep learning is challenging because of their enormous size, often millions or even billions of pixels.

Typical solutions drastically downsample the image uniformly to meet memory constraints, implicitly assuming all pixels equally important

… show that learning the spatially varying downsampling strategy jointly with segmentation offers advantages in segmenting large images with limited computational budget.

… method adapts the sampling density over different locations so that more samples are collected from the small important regions and less from the others, which in turn leads to better segmentation accuracy.

… method consistently learns sampling locations preserving more information and boosting segmentation accuracy over baseline methods.

Stay up to date. Subscribe to my posts https://morrislee1234.wixsite.com/website/contact
Web site with my other posts by category https://morrislee1234.wixsite.com/website

LinkedIn https://www.linkedin.com/in/morris-lee-47877b7b

Photo by Tengyart on Unsplash

--

--

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store
AI News Clips by Morris Lee: News to help your R&D

I apply innovative technologies like machine learning, computer vision, and physics to further an organization's goals. Am recognized innovator with 66 patents.