Segment unknown objects using top-down learning and bottom-up segmentations with UDOS
Segment unknown objects using top-down learning and bottom-up segmentations with UDOS
Open-world Instance Segmentation: Top-down Learning with Bottom-up Supervision
arXiv paper abstract https://arxiv.org/abs/2303.05503
arXiv PDF paper https://arxiv.org/pdf/2303.05503.pdf
Project page https://tarun005.github.io/UDOS
Many top-down architectures for instance segmentation achieve significant success when trained and tested on pre-defined closed-world taxonomy.
However, when deployed in the open world, they exhibit notable bias towards seen classes and suffer from significant performance drop.
... propose ... approach for open world instance segmentation called bottom-Up and top-Down Open-world Segmentation (UDOS) that combines classical bottom-up segmentation algorithms within a top-down learning framework.
UDOS first predicts parts of objects using a top-down network trained with weak supervision from bottom-up segmentations. The bottom-up segmentations are class-agnostic and do not overfit to specific taxonomies.
The part-masks are then fed into affinity-based grouping and refinement modules to predict robust instance-level segmentations. UDOS enjoys both the speed and efficiency from the top-down architectures and the generalization ability to unseen categories from bottom-up supervision.
... UDOS ... achieving significant improvements over state-of-the-art across the board ...
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