Segmentation system marks unknown objects which are then incrementally learned

Segmentation system marks unknown objects which are then incrementally learned

Deep Metric Learning for Open World Semantic Segmentation

arXiv paper abstract https://arxiv.org/abs/2108.04562v1

arXiv PDF paper https://arxiv.org/pdf/2108.04562v1.pdf

Classical ... segmentation networks have limited ability to detect out-of-distribution (OOD) objects, which is important for safety-critical applications such as autonomous driving.

... propose ... includes two modules:

(1) ... detect both in-distribution and OOD objects.

(2) an incremental few-shot learning module to gradually incorporate those OOD objects into its existing knowledge base.

... system behaves like a human being, which is able to identify OOD objects and gradually learn them with corresponding supervision.

... DMLNet achieves state-of-the-art performance on three challenging open-set semantic segmentation datasets without using additional data or generative 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 #ComputerVision #Segmentation #AINewsClips #AI #ML #ArtificialIntelligence #MachineLearning