Enhanced-feature pyramid network for semantic segmentation

Van Toan Quyen, Jong Hyuk Lee, Min Young Kim

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

2 Scopus citations

Abstract

Semantic segmentation is a complicated topic when they require strictly the object boundary accuracy. For autonomous driving applications, they have to face a long range of objective sizes in the street scenes, so a single field of views is not suitable to extract input features. Feature pyramid network (FPN) is an effective method for computer vision tasks such as object detection and semantic segmentation. The architecture of this approach composes of a bottom-up pathway and a top-down pathway. Based on the structure, we can obtain rich spatial information from the largest layer and extract rich segmentation information from lower-scale features. The traditional FPN efficiently captures different objective sizes by using multiple receptive fields and then predicts the outputs from the concatenated features. The final feature combination is not optimistic when they burden the hardware with huge computation and reduce the semantic information. In this paper, we propose multiple predictions for semantic segmentation. Instead of combining four-feature scales together, the proposed method processes separately three lower scales as the contextual contributor and the largest features as the coarser-information branch. Each contextual feature is concatenated with the coarse branch to generate an individual prediction. By deploying this architecture, a single prediction effectively segments specific objective sizes. Finally, score maps are fused together in order to gather the prominent weights from the different predictions. A series of experiments is implemented to validate the efficiency on various open data sets. We have achieved good results 76.4% mIoU at 52 FPS on Cityscapes and 43.6% m IoU on Mapillary Vistas.

Original languageEnglish
Title of host publication5th International Conference on Artificial Intelligence in Information and Communication, ICAIIC 2023
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages782-787
Number of pages6
ISBN (Electronic)9781665456456
DOIs
StatePublished - 2023
Event5th International Conference on Artificial Intelligence in Information and Communication, ICAIIC 2023 - Virtual, Online, Indonesia
Duration: 20 Feb 202323 Feb 2023

Publication series

Name5th International Conference on Artificial Intelligence in Information and Communication, ICAIIC 2023

Conference

Conference5th International Conference on Artificial Intelligence in Information and Communication, ICAIIC 2023
Country/TerritoryIndonesia
CityVirtual, Online
Period20/02/2323/02/23

Keywords

  • Semantic segmentation
  • feature pyramid network
  • multiscale prediction
  • real-time application

Fingerprint

Dive into the research topics of 'Enhanced-feature pyramid network for semantic segmentation'. Together they form a unique fingerprint.

Cite this