Work

Transformer-Based Decoder Designs for Semantic Segmentation on Remotely Sensed Images

Year: 2021

Type: article

Abstract: Transformers have demonstrated remarkable accomplishments in several natural language processing (NLP) tasks as well as image processing tasks. Herein, we present a deep-learning (DL) model that is capable of improving the semantic segmentation network in two ways. First, utilizing the pre-training Swin Transformer (SwinTF) under Vision Transformer (ViT) as a backbone, the model weights downstream tasks by joining task layers upon the pretrained encoder. Secondly, decoder designs are applied to our DL network with three decoder designs, U-Net, pyramid scene parsing (PSP) network, and feature pyramid network (FPN), to perform pixel-level segmentation. The results are compared with other image labeling state of the art (SOTA) methods, such as global convolutional network (GCN) and ViT. Extensive experiments show that our Swin Transformer (SwinTF) with decoder designs reached a new state of the art on the Thailand Isan Landsat-8 corpus (89.8% F1 score), Thailand North Landsat-8 corpus (63.12% F1 score), and competitive results on ISPRS Vaihingen. Moreover, both our best-proposed methods (SwinTF-PSP and SwinTF-FPN) even outperformed SwinTF with supervised pre-training ViT on the ImageNet-1K in the Thailand, Landsat-8, and ISPRS Vaihingen corpora.

Source: Remote Sensing

DOI: 10.3390/rs13245100

Authors: Teerapong Panboonyuen, Kulsawasd Jitkajornwanich, Siam Lawawirojwong, Panu Srestasathiern, Peerapon Vateekul

Institutions: Chulalongkorn University, King Mongkut's Institute of Technology Ladkrabang

Language: English

Topic: Remote-Sensing Image Classification

Subfield: Media Technology

Field: Engineering

Domain: Physical Sciences

Open Access status: gold

Estimated APC paid: $2,592

Funder: Chulalongkorn University