☆ 4.7 Article

CNN, RNN, or ViT? An Evaluation of Different Deep Learning Architectures for Spatio-Temporal Representation of Sentinel Time Series

IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING (2023)

Related references

Note: Only part of the references are listed.

Article Environmental Sciences

Swin Transformer and Deep Convolutional Neural Networks for Coastal Wetland Classification Using Sentinel-1, Sentinel-2, and LiDAR Data

Ali Jamali et al.

Summary: This study explores the potential and limitations of integrating deep learning networks with transformers for complex coastal wetland classification. The results demonstrate that the multi-model network outperforms other solo classifiers in wetland classification.

REMOTE SENSING (2022)

Add to Collection

Article Environmental Sciences

Fusion Classification of HSI and MSI Using a Spatial-Spectral Vision Transformer for Wetland Biodiversity Estimation

Yunhao Gao et al.

Summary: This paper proposes a systematic framework for multisource remote sensing image processing, which fuses hyperspectral and multispectral images and utilizes a spatial-spectral vision transformer to extract sequential relationships, achieving accurate land-cover mapping.

REMOTE SENSING (2022)

Add to Collection

Proceedings Paper Geosciences, Multidisciplinary

DUAL-TASKS SIAMESE TRANSFORMER FRAMEWORK FOR BUILDING DAMAGE ASSESSMENT

Hongruixuan Chen et al.

Summary: In this paper, a Transformer-based architecture called DamFormer is proposed for damage assessment. It utilizes a siamese Transformer encoder to extract non-local and representative deep features, a multitemporal fusion module to fuse information, and a lightweight dual-tasks decoder for final prediction. Experimental results demonstrate the potential of this Transformer-based architecture in remote sensing interpretation tasks.

2022 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM (IGARSS 2022) (2022)

Add to Collection

Article Geochemistry & Geophysics

Multiscale Progressive Segmentation Network for High-Resolution Remote Sensing Imagery

Renlong Hang et al.

Summary: This article proposes a multiscale progressive segmentation network for semantic segmentation of high-resolution remote sensing imageries. The network adopts cascaded subnetworks and a scale guidance module to gradually segment objects of different scales. Additionally, a position-sensitive module is proposed to adaptively combine the outputs of the subnetworks for acquiring the final segmentation results.

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING (2022)

Add to Collection

Article Engineering, Electrical & Electronic

Attentional Dense Convolutional Neural Network for Water Body Extraction From Sentinel-2 Images

Janak Parajuli et al.

Summary: This article presents a new attentional dense convolutional neural network (AD-CNN) for water body extraction from Sentinel-2 imagery. The AD-CNN exploits dense connections to uncover deeper features and implements a residual attention module to dynamically focus on relevant features. Experimental results show that the proposed method achieves competitive performance.

IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING (2022)

Add to Collection

Article Geochemistry & Geophysics

Cross-Modality Contrastive Learning for Hyperspectral Image Classification

Renlong Hang et al.

Summary: Unsupervised feature learning with multimodal data can address the issue of labeling in hyperspectral image classification, and the dual fine-tuning strategy improves the classification performance.

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING (2022)

Add to Collection

Article Geochemistry & Geophysics

A ViT-Based Multiscale Feature Fusion Approach for Remote Sensing Image Segmentation

Wei Wang et al.

Summary: Semantic segmentation is essential for automatic analysis of remote sensing images. However, the utilization of abundant semantic information and irregular shape patterns in these images is challenging. To address this, a multiscale feature pyramid decoder (MFPD) is proposed to fuse image features extracted by vision transformer (ViT). The decoder employs a 2-D-to-3-D transform method to obtain multiscale feature maps and uses channel concatenation for fusion. A dimension attention module (DAM) is also designed to aggregate context information. Experimental results show that this approach outperforms other methods based on convolutional neural networks (CNN) and ViT in terms of mean intersection over union (mIoU).

IEEE GEOSCIENCE AND REMOTE SENSING LETTERS (2022)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

UNETR: Transformers for 3D Medical Image Segmentation

Ali Hatamizadeh et al.

Summary: Fully Convolutional Neural Networks (FCNNs) have been successful in medical image segmentation, but their limited ability to learn long-range dependencies is a challenge. Inspired by transformers in NLP, we propose a novel architecture called UNet Transformers (UNETR) to redefine volumetric medical image segmentation as a sequence prediction problem. By combining transformers and U-shaped network design in the encoder and decoder, we effectively capture global information and achieve semantic segmentation output.

2022 IEEE WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION (WACV 2022) (2022)

Add to Collection

Article Geochemistry & Geophysics

DisOptNet: Distilling Semantic Knowledge From Optical Images for Weather-Independent Building Segmentation

Jian Kang et al.

Summary: Synthetic aperture radar (SAR) images have been widely used in intelligent remote sensing (RS) image interpretation, especially under poor weather conditions. However, compared to optical images, SAR images have less rich and interpretable semantics. In this article, a novel method based on the DisOptNet network is proposed to improve segmentation performance through knowledge transfer from optical images. Experimental results demonstrate the effectiveness of DisOptNet in generating building footprints under real scenarios.

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING (2022)

Add to Collection

Article Geochemistry & Geophysics

Hyperspectral Image Classification With Attention-Aided CNNs

Renlong Hang et al.

Summary: An attention-aided CNN model for spectral-spatial classification of hyperspectral images is proposed, which integrates spectral and spatial attention subnetworks to focus on discriminative features. Experimental results demonstrate the superior performance of the proposed model compared to state-of-the-art CNN-related models.

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING (2021)

Add to Collection

Article Environmental Sciences

Spatial and temporal deep learning methods for deriving land-use following deforestation: A pan-tropical case study using Landsat time series

Robert N. Masolele et al.

Summary: This study assessed land-use classification methods following deforestation, finding that spatio-temporal models outperformed spatial or temporal models. Spatial patterns of land-use within a continent had more commonalities than temporal patterns across continents.

REMOTE SENSING OF ENVIRONMENT (2021)

Add to Collection

Article Geography, Physical

Field-scale crop yield prediction using multi-temporal WorldView-3 and PlanetScope satellite data and deep learning

Vasit Sagan et al.

Summary: This study successfully developed a deep learning approach based on raw satellite imagery for field-scale yield prediction, demonstrating that deep learning can predict yield directly and explain nearly 90% variance. The use of WV-3 imagery with RedEdge and SWIR bands outperformed multi-temporal PS data for yield prediction.

ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING (2021)

Add to Collection

Article Environmental Sciences

Efficient Transformer for Remote Sensing Image Segmentation

Zhiyong Xu et al.

Summary: This study introduces a novel Efficient Transformer model to address edge classification issues in remote sensing image semantic segmentation, significantly improving accuracy while balancing computational complexity. By accelerating inference speed and introducing edge enhancement methods, improvements were achieved on the Potsdam and Vaihingen datasets.

REMOTE SENSING (2021)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

ViViT: A Video Vision Transformer

Anurag Arnab et al.

Summary: The study introduces Transformer-based video classification models and achieves state-of-the-art results on multiple benchmarks. Researchers demonstrate how to train the model on smaller datasets and improve performance by leveraging pretrained image models.

2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021) (2021)

Add to Collection

Article Environmental Sciences

Deep learning based multi-temporal crop classification

Liheng Zhong et al.

REMOTE SENSING OF ENVIRONMENT (2019)

Add to Collection

Article Environmental Sciences

A Novel Spatio-Temporal FCN-LSTM Network for Recognizing Various Crop Types Using Multi-Temporal Radar Images

Nima Teimouri et al.

REMOTE SENSING (2019)

Add to Collection

Article Environmental Sciences

Comparing Thresholding with Machine Learning Classifiers for Mapping Complex Water

Tsitsi Bangira et al.

REMOTE SENSING (2019)

Add to Collection

Article Geochemistry & Geophysics

Deep Learning for Hyperspectral Image Classification: An Overview

Shutao Li et al.

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING (2019)

Add to Collection

Article Geochemistry & Geophysics

Cascaded Recurrent Neural Networks for Hyperspectral Image Classification

Renlong Hang et al.

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING (2019)

Add to Collection

Article Geochemistry & Geophysics

Nonlocal Filtering Applied to 3-D Reconstruction of Tomographic SAR Data

Olivier D'Hondt et al.

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING (2018)

Add to Collection

Article Environmental Sciences

3D Convolutional Neural Networks for Crop Classification with Multi-Temporal Remote Sensing Images

Shunping Ji et al.

REMOTE SENSING (2018)

Add to Collection

Article Computer Science, Information Systems

Multi-Temporal Land Cover Classification with Sequential Recurrent Encoders

Marc Russwurm et al.

ISPRS INTERNATIONAL JOURNAL OF GEO-INFORMATION (2018)

Add to Collection

Article Geochemistry & Geophysics

Deep Learning Classification of Land Cover and Crop Types Using Remote Sensing Data

Nataliia Kussul et al.

IEEE GEOSCIENCE AND REMOTE SENSING LETTERS (2017)

Add to Collection

Article Meteorology & Atmospheric Sciences

Objective climate classification of Slovenia

Katja Kozjek et al.

INTERNATIONAL JOURNAL OF CLIMATOLOGY (2017)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

Convolutional Gated Recurrent Neural Network Incorporating Spatial Features for Audio Tagging

Yong Xu et al.

2017 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN) (2017)

Add to Collection

Article Geochemistry & Geophysics

Deep Feature Extraction and Classification of Hyperspectral Images Based on Convolutional Neural Networks

Yushi Chen et al.

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING (2016)

Add to Collection

Article Geochemistry & Geophysics

Deep Learning for Remote Sensing Data A technical tutorial on the state of the art

Liangpei Zhang et al.

IEEE GEOSCIENCE AND REMOTE SENSING MAGAZINE (2016)

Add to Collection

Article Computer Science, Artificial Intelligence

3D Convolutional Neural Networks for Human Action Recognition

Shuiwang Ji et al.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2013)

Add to Collection

Article Engineering, Environmental

The impacts of watershed management on land use and land cover dynamics in Eastern Tigray (Ethiopia)

Fikir Alemayehu et al.

RESOURCES CONSERVATION AND RECYCLING (2009)

Add to Collection

Article Environmental Sciences

Analysis of time-series MODIS 250 m vegetation index data for crop classification in the US Central Great Plains

Brian D. Wardlow et al.

REMOTE SENSING OF ENVIRONMENT (2007)

Add to Collection

Article Environmental Sciences

Mapping paddy rice agriculture in southern China using multi-temporal MODIS images

XM Xiao et al.

REMOTE SENSING OF ENVIRONMENT (2005)

Add to Collection

Article Computer Science, Artificial Intelligence

Random forests

L Breiman

MACHINE LEARNING (2001)

Add to Collection

Article Ecology

Assessing the environmental performance of land cover types for urban planning

S Pauleit et al.

LANDSCAPE AND URBAN PLANNING (2000)

Add to Collection

© Peeref 2019-2024. All rights reserved.