Deep Ensembles for Semantic Segmentation on Road Detection

Deniz Uzun, Dewei Yi

Research output: Chapter in Book/Report/Conference proceedingPublished conference contribution

Abstract

Semantic segmentation is a significant technique that can provide valuable insights into the context of driving scenes. This work discusses several mechanisms: data augmentation, transfer learning, transposed convolutions and focal loss function for improving the performance of neural networks for image segmentation. Experiments on two traditional model architectures-U-net and MobileUNetV2-are conducted and the results are evaluated in terms of-Intersection-over-Union (IoU) and F-score. The KITTI Road dataset is utilised for training and testing the algorithms on road segmentation. More specifically, data augmentation and the task-specific focal loss provide the highest improvement of 6.68% and 5.23%, respectively. To further enhance segmentation performance, an ensemble scheme is adopted where several models are executed simultaneously and their outputs are fused together to derive the final prediction. Such a design can reduce incorrect predictions of individual models and produce more precise segmentation masks.

Original languageEnglish
Title of host publicationProceedings of the 26 th International Conference on Automation & Computing
Subtitle of host publicationSystem Intelligence through Automation and Computing, ICAC 2021
EditorsChenguang Yang
PublisherIEEE Explore
ISBN (Electronic)9781860435577
DOIs
Publication statusPublished - 2021
Event26th International Conference on Automation and Computing, ICAC 2021 - Portsmouth, United Kingdom
Duration: 2 Sep 20214 Sep 2021

Publication series

Name2021 26th International Conference on Automation and Computing: System Intelligence through Automation and Computing, ICAC 2021

Conference

Conference26th International Conference on Automation and Computing, ICAC 2021
Country/TerritoryUnited Kingdom
CityPortsmouth
Period2/09/214/09/21

Keywords

  • segmentation
  • focal loss
  • transfer learning
  • ensmeble scheme
  • data augmentation

Fingerprint

Dive into the research topics of 'Deep Ensembles for Semantic Segmentation on Road Detection'. Together they form a unique fingerprint.

Cite this