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

05/02/2023
by   Markus Schön, et al.
0

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 resolution 1024x2048 pixel images on a single Titan RTX GPU. On Mapillary Vistas, RT-K-Net reaches 33.2 Source code is available at https://github.com/markusschoen/RT-K-Net.

READ FULL TEXT

page 4

page 7

research
04/17/2019

nnU-Net: Breaking the Spell on Successful Medical Image Segmentation

Fueled by the diversity of datasets, semantic segmentation is a popular ...
research
12/12/2018

CFUN: Combining Faster R-CNN and U-net Network for Efficient Whole Heart Segmentation

In this paper, we propose a novel heart segmentation pipeline Combining ...
research
07/27/2022

Lightweight and Progressively-Scalable Networks for Semantic Segmentation

Multi-scale learning frameworks have been regarded as a capable class of...
research
05/16/2018

Deep Segmentation and Registration in X-Ray Angiography Video

In interventional radiology, short video sequences of vein structure in ...
research
08/12/2023

LadleNet: Translating Thermal Infrared Images to Visible Light Images Using A Scalable Two-stage U-Net

The translation of thermal infrared (TIR) images to visible light (VI) i...
research
06/11/2019

Recurrent U-Net for Resource-Constrained Segmentation

State-of-the-art segmentation methods rely on very deep networks that ar...
research
07/28/2021

TEDS-Net: Enforcing Diffeomorphisms in Spatial Transformers to Guarantee Topology Preservation in Segmentations

Accurate topology is key when performing meaningful anatomical segmentat...

Please sign up or login with your details

Forgot password? Click here to reset