Improve segmentation of unknown objects by using a single stage with SOIS

Improve segmentation of unknown objects by using a single stage with SOIS

Single-Stage Open-world Instance Segmentation with Cross-task Consistency Regularization

arXiv paper abstract https://arxiv.org/abs/2208.09023v1

arXiv PDF paper https://arxiv.org/pdf/2208.09023v1.pdf

Open-world instance segmentation (OWIS) aims to segment class-agnostic instances from images, which has a wide range of real-world applications such as autonomous driving.

Most existing approaches follow a two-stage pipeline: performing class-agnostic detection first and then class-specific mask segmentation.

... proposes a single-stage framework to produce a mask for each instance directly.

... first train an extra branch to perform an auxiliary task of predicting foreground regions (i.e. regions belonging to any object instance), and then encourage the prediction from the auxiliary branch to be consistent with the predictions of the instance masks.

... demonstrate that the proposed method can achieve impressive results in both fully-supervised and semi-supervised settings.

... In ... semi-supervised learning, ... model learned with only 30% labeled data, even outperforms its fully-supervised counterpart with 50% labeled data ...

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 LinkedIn https://www.linkedin.com/in/morris-lee-47877b7b #ComputerVision #Segmentation #AINewsClips #AI #ML #ArtificialIntelligence #MachineLearning