Real-time segmentation using improved K-Net architecture with RT-K-Net
Real-time segmentation using improved K-Net architecture with RT-K-Net
RT-K-Net: Revisiting K-Net for Real-Time Panoptic Segmentation
arXiv paper abstract https://arxiv.org/abs/2305.01255
arXiv PDF paper https://arxiv.org/pdf/2305.01255.pdf
Panoptic segmentation is one of the most challenging scene parsing tasks, combining the tasks of semantic segmentation and instance segmentation.
... few works focus on the real-time application of panoptic segmentation methods.
... revisit the recently introduced K-Net architecture.
... propose vital changes to the architecture, training, and inference procedure, which massively decrease latency and improve performance.
... resulting RT-K-Net sets a new state-of-the-art performance for real-time panoptic segmentation methods on the Cityscapes dataset and shows promising results on the challenging Mapillary Vistas dataset.
On Cityscapes, RT-K-Net reaches 60.2 % PQ with an average inference time of 32 ms for full resolution 1024x2048 pixel images on a single Titan RTX GPU ...
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