TrSeg: Transformer for semantic segmentation

Youngsaeng Jin, David Han, Hanseok Ko

Research output: Contribution to journalArticlepeer-review

Abstract

Recent efforts in semantic segmentation using deep learning frameworks have made notable advances. However, capturing the existence of objects in an image at multiple scales still remains a challenge. In this paper, we address the semantic segmentation task based on transformer architecture. Unlike existing methods that capture multi-scale contextual information through infusing every single-scale piece of information from parallel paths, we propose a novel semantic segmentation network incorporating a transformer (TrSeg) to adaptively capture multi-scale information with the dependencies on original contextual information. Given the original contextual information as keys and values, the multi-scale contextual information from the multi-scale pooling module as queries is transformed by the transformer decoder. The experimental results show that TrSeg outperforms the other methods of capturing multi-scale information by large margins.

Original languageEnglish
Pages (from-to)29-35
Number of pages7
JournalPattern Recognition Letters
Volume148
DOIs
Publication statusPublished - 2021 Aug

Keywords

  • Multi-scale contextual information
  • Scene understanding
  • Semantic segmentation
  • Transformer

ASJC Scopus subject areas

  • Software
  • Signal Processing
  • Computer Vision and Pattern Recognition
  • Artificial Intelligence

Fingerprint

Dive into the research topics of 'TrSeg: Transformer for semantic segmentation'. Together they form a unique fingerprint.

Cite this