Panoptic SwiftNet: Pyramidal Fusion for Real-time Panoptic Segmentation

03/15/2022
by   Josip Šarić, et al.
0

Dense panoptic prediction is a key ingredient in many existing applications such as autonomous driving, automated warehouses or agri-robotics. However, most of these applications leverage the recovered dense semantics as an input to visual closed-loop control. Hence, practical deployments require real-time inference over large input resolutions on embedded hardware. These requirements call for computationally efficient approaches which deliver high accuracy with limited computational resources. We propose to achieve this goal by trading-off backbone capacity for multi-scale feature extraction. In comparison with contemporaneous approaches to panoptic segmentation, the main novelties of our method are scale-equivariant feature extraction and cross-scale upsampling through pyramidal fusion. Our best model achieves 55.9 60 FPS on full resolution 2MPx images and RTX3090 with FP16 Tensor RT optimization.

READ FULL TEXT

page 2

page 3

page 5

page 6

page 7

research
03/01/2022

Boundary Corrected Multi-scale Fusion Network for Real-time Semantic Segmentation

Image semantic segmentation aims at the pixel-level classification of im...
research
02/13/2023

CFNet: Cascade Fusion Network for Dense Prediction

Multi-scale features are essential for dense prediction tasks, including...
research
06/08/2021

CSRNet: Cascaded Selective Resolution Network for Real-time Semantic Segmentation

Real-time semantic segmentation has received considerable attention due ...
research
04/29/2015

Hardware based Scale- and Rotation-Invariant Feature Extraction: A Retrospective Analysis and Future Directions

Computer Vision techniques represent a class of algorithms that are high...
research
03/23/2022

Revisiting Multi-Scale Feature Fusion for Semantic Segmentation

It is commonly believed that high internal resolution combined with expe...
research
07/27/2020

YOLOpeds: Efficient Real-Time Single-Shot Pedestrian Detection for Smart Camera Applications

Deep Learning-based object detectors can enhance the capabilities of sma...
research
07/16/2021

DANCE: DAta-Network Co-optimization for Efficient Segmentation Model Training and Inference

Semantic segmentation for scene understanding is nowadays widely demande...

Please sign up or login with your details

Forgot password? Click here to reset