Improved object segmentation using feature and mask guidance with IS-Net
Improved object segmentation using feature and mask guidance with IS-Net
Highly Accurate Dichotomous Image Segmentation
arXiv paper abstract https://arxiv.org/abs/2203.03041
arXiv PDF paper https://arxiv.org/pdf/2203.03041.pdf
Twitter video https://twitter.com/_akhaliq/status/1549841365814632452
Project page https://xuebinqin.github.io/dis/index.html
... present a systematic study on a new task called dichotomous image segmentation (DIS) , which aims to segment highly accurate objects from natural images.
... collected the first large-scale DIS dataset, called DIS5K, ... covering camouflaged, salient, or meticulous objects in various backgrounds.
... introduce a simple intermediate supervision baseline (IS-Net) using both feature-level and mask-level guidance for DIS model training.
IS-Net outperforms various cutting-edge baselines on the proposed DIS5K, making it a general self-learned supervision network that can facilitate future research in DIS.
... design a new metric called human correction efforts (HCE) which approximates the number of mouse clicking operations required to correct the false positives and false negatives.
... conduct the largest-scale benchmark, evaluating 16 representative segmentation models ...
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
Comentários