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.
Please like and share this post if you enjoyed it using the buttons at the bottom!
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
#ComputerVision #Segmentation #AINewsClips #AI #ML #ArtificialIntelligence #MachineLearning
Comments