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

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

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...

Full description

Bibliographic Details
Main Authors: Teerapong Panboonyuen, Kulsawasd Jitkajornwanich, Siam Lawawirojwong, Panu Srestasathiern, Peerapon Vateekul
Format: Article
Language:English
Published: MDPI AG 2021-12-01
Series:Remote Sensing
Subjects:
vision transformer
fully transformer networks
convolutional neural network
feature pyramid network
high-resolution representations
ISPRS Vaihingen
Online Access:https://www.mdpi.com/2072-4292/13/24/5100

Internet

https://www.mdpi.com/2072-4292/13/24/5100

Similar Items