Segment objects of any type in image using model trained without manual annotations with FreeSOLO
Segment objects of any type in image using model trained without manual annotations with FreeSOLO
FreeSOLO: Learning to Segment Objects without Annotations
arXiv paper abstract https://arxiv.org/abs/2202.12181
arXiv PDF paper https://arxiv.org/pdf/2202.12181.pdf
Instance segmentation ... aims to recognize and segment each object in an image.
However, it requires costly annotations such as bounding boxes and segmentation masks for learning.
... propose a fully unsupervised learning method that learns class-agnostic instance segmentation without any annotations.
... present FreeSOLO, a self-supervised instance segmentation framework built on top of the simple instance segmentation method SOLO.
FreeSOLO achieves 9.8% AP50 on the challenging COCO dataset, which even outperforms several segmentation proposal methods that use manual annotations.
... FreeSOLO's box localization ... outperforms state-of-the-art unsupervised object detection/discovery methods, with about 100% relative improvements in COCO AP. ...
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
Comments