Journal article
TrSeg: Transformer for semantic segmentation
Pattern recognition letters, v 148
01 Aug 2021
Featured in Collection : UN Sustainable Development Goals @ Drexel
Abstract
Recent effort s in semantic segment ation 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 exist-ing 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 con-textual information. Given the original contextual information as keys and values, the multi-scale con-textual 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. (c) 2021 Elsevier B.V. All rights reserved.
Metrics
Details
- Title
- TrSeg: Transformer for semantic segmentation
- Creators
- Youngsaeng Jin - Wrexham UniversityDavid Han - Drexel UniversityHanseok Ko - The School of Electrical Engineering at Korea Unversity, 145 Anam-ro, Seongbuk-gu, Seoul, 02841, South Korea
- Publication Details
- Pattern recognition letters, v 148
- Publisher
- Elsevier
- Number of pages
- 7
- Grant note
- FA2386-19-1-4001 / Air Force Office of Scientific Research; United States Department of Defense; Air Force Office of Scientific Research (AFOSR)
- Resource Type
- Journal article
- Language
- English
- Academic Unit
- Electrical and Computer Engineering
- Web of Science ID
- WOS:000674680600005
- Scopus ID
- 2-s2.0-85106916179
- Other Identifier
- 991019168228504721
UN Sustainable Development Goals (SDGs)
This publication has contributed to the advancement of the following goals:
InCites Highlights
Data related to this publication, from InCites Benchmarking & Analytics tool:
- Collaboration types
- International collaboration
- Web of Science research areas
- Computer Science, Artificial Intelligence