Logo image
TrSeg: Transformer for semantic segmentation
Journal article   Open access   Peer reviewed

TrSeg: Transformer for semantic segmentation

Youngsaeng Jin, David Han and Hanseok Ko
Pattern recognition letters, v 148
01 Aug 2021
url
https://doi.org/10.1016/j.patrec.2021.04.024View
Accepted (AM)Maybe Open Access (Publisher Bronze) Open

Abstract

Computer Science Computer Science, Artificial Intelligence Science & Technology Technology
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

16 Record Views
86 citations in Scopus

Details

UN Sustainable Development Goals (SDGs)

This publication has contributed to the advancement of the following goals:

#3 Good Health and Well-Being

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
Logo image