TrSeg: Transformer for semantic segmentation
- Authors
- Jin, Y.; Han, D.; Ko, H.
- Issue Date
- 2021
- Publisher
- Elsevier B.V.
- Keywords
- Multi-scale contextual information; Scene understanding; Semantic segmentation; Transformer
- Citation
- Pattern Recognition Letters, v.148, pp.29 - 35
- Indexed
- SCIE
SCOPUS
- Journal Title
- Pattern Recognition Letters
- Volume
- 148
- Start Page
- 29
- End Page
- 35
- URI
- https://scholar.korea.ac.kr/handle/2021.sw.korea/137913
- DOI
- 10.1016/j.patrec.2021.04.024
- ISSN
- 0167-8655
- 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. © 2021 Elsevier B.V.
- Files in This Item
- There are no files associated with this item.
- Appears in
Collections - College of Engineering > School of Electrical Engineering > 1. Journal Articles
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.