RT-K-Net: Revisiting K-Net for Real-Time Panoptic Segmentation

• Published in: 2023 IEEE Intelligent Vehicles Symposium (IV) pp. 1 - 7
• Main Authors: Schon, Markus, Buchholz, Michael, Dietmayer, Klaus
• Format: Conference Proceeding
• Language: English
• Published: IEEE 04.06.2023
• Subjects: Graphics processing units; Image resolution; Intelligent vehicles; Panoptic Segmentation; Real-Time Processing; Real-time systems; Scene Understanding; Semantic segmentation; Source coding; Training
• ISSN: 2642-7214
• DOI: 10.1109/IV55152.2023.10186625

Panoptic segmentation is one of the most challenging scene parsing tasks, combining the tasks of semantic segmentation and instance segmentation. While much progress has been made, few works focus on the real-time application of panoptic segmentation methods. In this paper, we revisit the recently introduced K-Net architecture. We propose vital changes to the architecture, training, and inference procedure, which massively decrease latency and improve performance. Our 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 1024×2048 pixel images on a single Titan RTX GPU. On Mapillary Vistas, RT-K-Net reaches 33.2 % PQ with an average inference time of 69 ms. Source code is available at https://github.com/markusschoen/RT-K-Net.