Premium
Benchmarking pre‐trained Encoders for real‐time Semantic Road Scene Segmentation
Author(s) -
Evers Lennart
Publication year - 2021
Publication title -
pamm
Language(s) - English
Resource type - Journals
ISSN - 1617-7061
DOI - 10.1002/pamm.202000275
Subject(s) - computer science , benchmarking , encoder , segmentation , benchmark (surveying) , artificial intelligence , convolutional neural network , inference , task (project management) , modular design , semantics (computer science) , pattern recognition (psychology) , computer vision , machine learning , artificial neural network , engineering , geodesy , systems engineering , marketing , business , programming language , geography , operating system
Semantic segmentation, i.e. assigning each pixel in an image a class to which it belongs, can be a part of the implementation for the perception model of autonomous vehicles. Over the last years multiple powerful neural network architectures for solving this task have been developed. In this work, a simple lightweight but modular, fully convolutional encoder‐decoder network has been implemented and multiple, publicly available pre‐trained classification networks are evaluated on their encoder performance on the Cityscapes [8] benchmark dataset with respect to their accuracy and their inference speed.