.png){kind=icon}
.png){kind=icon}
Return
Omnisupervised Omnidirectional Semantic Segmentation
.png){kind=icon}
PRE
AI
DOI：10.1109/TITS.2020.3023331.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Modern efficient Convolutional Neural Networks (CNNs) are able to perform semantic segmentation both swiftly and accurately, which covers typically separate detection tasks desired by Intelligent Vehicles (IV) in a unified way. Most of the current semantic perception frameworks are designed to work with pinhole cameras and benchmarked against public datasets with narrow Field-of-View (FoV) images. However, there is a large accuracy downgrade when a pinhole-yielded CNN is taken to omnidirectional imagery, causing it unreliable for surrounding perception. In this paper, we propose an omnisupervised learning framework for efficient CNNs, which bridges multiple heterogeneous data sources that are already available in the community, bypassing the labor-intensive process to have manually annotated panoramas, while improving their reliability in unseen omnidirectional domains. Being omnisupervised, the efficient CNN exploits both labeled pinhole images and unlabeled panoramas. The framework is based on our specialized ensemble method that considers the wide-angle and wrap-around features of omnidirectional images, to automatically generate panoramic labels for data distillation. A comprehensive variety of experiments demonstrates that the proposed solution helps to attain significant generalizability gains in panoramic imagery domains. Our approach outperforms state-of-the-art efficient segmenters on highly unconstrained IDD20K and PASS datasets.
Keywords:
Semantics
Image segmentation
Training
Data models
Sensors
Task analysis
Cameras
Intelligent vehicles
scene understanding
semantic segmentation
scene parsing
omnisupervised learning
omnidirectional images
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
8.4
Papers:
9.5K
Citations:
6.3W