Deep Domain Adaptation in Earth Observation

Kellenberger, Benjamin; Taşar, Onur; Damodaran, Bharath Bhushan; Courty, Nicolas; Tuia, Devis

doi:10.1002/9781119646181.ch7

Cited by 13 publications

(6 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…When there is a significant divergence between the train and test data distributions, a model trained on the former will likely fail to generalize on the latter, and thus, performance will be greatly degraded. A popular approach which attempts to tackle this problem is domain adaptation (DA), a special branch of transfer learning which aims to alleviate the variation between the source (train set) and target (test set) data distributions caused by data shift, concept drift, and multimodal domain shift often observed in remote sensing data [33]. Data shift describes the spectral differences between images captured under different conditions, i.e., different atmospheric effects, sun positions, sensor angles, etc.…”

Section: Domain Adaptationmentioning

confidence: 99%

A Sentinel-2 Multiyear, Multicountry Benchmark Dataset for Crop Classification and Segmentation With Deep Learning

Sykas

Sdraka

Zografakis

et al. 2022

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

In this work, we introduce Sen4AgriNet, a Sentinel-2-based time series multicountry benchmark dataset, tailored for agricultural monitoring applications with machine and deep learning. Sen4AgriNet dataset is annotated from farmer declarations collected via the land parcel identification system (LPIS) for harmonizing country-wide labels. These declarations have only recently been made available as open data, allowing for the first time the labeling of satellite imagery from ground truth data. We proceed to propose and standardize a new crop type taxonomy across Europe that addresses common agriculture policy (CAP) needs, based on the Food and Agriculture Organization (FAO) indicative crop classification scheme. Sen4AgriNet is the only multicountry, multiyear dataset that includes all spectral information. It is constructed to cover the period 2016-2020 for Catalonia and France, while it can be extended to include additional countries. Currently, it contains 42.5 million parcels, which makes it significantly larger than other available archives. We extract two subdatasets to highlight its value for diverse deep learning applications-the object aggregated dataset (OAD) and the patches assembled dataset (PAD). OAD capitalizes zonal statistics of each parcel, thus creating a powerful label-to-features instance for classification algorithms. On the other hand, PAD structure generalizes the classification problem to parcel extraction and semantic segmentation and labeling. The PAD and OAD are examined under three different scenarios to showcase and model the effects of spatial and temporal variability across different years and different countries. 1

show abstract

Section: Domain Adaptationmentioning

confidence: 99%

A Sentinel-2 Multiyear, Multicountry Benchmark Dataset for Crop Classification and Segmentation With Deep Learning

Sykas

Sdraka

Zografakis

et al. 2022

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

show abstract

“…Most of the current deep DA methods add adaptation layers to an original deep network architecture to realize the source-to-target adaptation or adopt an adversarial learning strategy to minimize the crossdomain discrepancy. Deep DA methods are mainly divided into discrepancy-based methods, adversarial-based methods and others [5], [159].…”

Section: Deep Domain Adaptationmentioning

confidence: 99%

Domain Adaptation in Remote Sensing Image Classification: A Survey

Peng

Huang

Sun

et al. 2022

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

Traditional remote sensing (RS) image classification methods heavily rely on labeled samples for model training. When labeled samples are unavailable or labeled samples have different distributions from that of the samples to be classified, the classification model may fail. The cross-domain or crossscene remote sensing image classification is developed for this case where an existing image for training and an unknown image from different scenes or domains for classification. The distribution inconsistency problem may be caused by the differences in acquisition environment conditions, acquisition scene, acquisition time or/and changing sensors. To cope with the cross-domain remote sensing image classification problem, many domain adaptation (DA) techniques have been developed. In this article, we review DA methods in the fields of RS, especially hyperspectral image classification, and provide a survey of DA methods into traditional shallow DA methods (e.g., instance-based, featurebased, and classifier-based adaptations) and recently developed deep DA methods (e.g., discrepancy-based and adversarial-based adaptations).

show abstract

“…When there is a significant divergence between the train and test data distributions, a model trained on the former will likely fail to generalize on the latter and thus performance will be greatly degraded. A popular approach which attempts to tackle this problem is Domain Adaptation (DA), a special branch of transfer learning which aims to alleviate the variation between the source (train set) and target (test set) data distributions caused by data shift, concept drift and multi-modal domain shift often observed in Remote Sensing data [33]. Data shift describes the spectral differences between images captured under different conditions, i.e.…”

Section: Domain Adaptationmentioning

confidence: 99%

A Sentinel-2 multi-year, multi-country benchmark dataset for crop classification and segmentation with deep learning

Sykas¹,

Sdraka²,

Zografakis³

et al. 2022

Preprint

View full text Add to dashboard Cite

In this work we introduce Sen4AgriNet, a Sentinel-2 based time series multi country benchmark dataset, tailored for agricultural monitoring applications with Machine and Deep Learning. Sen4AgriNet dataset is annotated from farmer declarations collected via the Land Parcel Identification System (LPIS) for harmonizing country wide labels. These declarations have only recently been made available as open data, allowing for the first time the labeling of satellite imagery from ground truth data. We proceed to propose and standardise a new crop type taxonomy across Europe that address Common Agriculture Policy (CAP) needs, based on the Food and Agriculture Organization (FAO) Indicative Crop Classification scheme. Sen4AgriNet is the only multi-country, multi-year dataset that includes all spectral information. It is constructed to cover the period 2016-2020 for Catalonia and France, while it can be extended to include additional countries. Currently, it contains 42.5 million parcels, which makes it significantly larger than other available archives. We extract two sub-datasets to highlight its value for diverse Deep Learning applications; the Object Aggregated Dataset (OAD) and the Patches Assembled Dataset (PAD). OAD capitalizes zonal statistics of each parcel, thus creating a powerful labelto-features instance for classification algorithms. On the other hand, PAD structure generalizes the classification problem to parcel extraction and semantic segmentation and labeling. The PAD and OAD are examined under three different scenarios to showcase and model the effects of spatial and temporal variability across different years and different countries. The dataset can be accessed in: https://sen4agrinet.space.noa.gr

show abstract

Deep Domain Adaptation in Earth Observation

Cited by 13 publications

References 0 publications

A Sentinel-2 Multiyear, Multicountry Benchmark Dataset for Crop Classification and Segmentation With Deep Learning

A Sentinel-2 Multiyear, Multicountry Benchmark Dataset for Crop Classification and Segmentation With Deep Learning

Domain Adaptation in Remote Sensing Image Classification: A Survey

A Sentinel-2 multi-year, multi-country benchmark dataset for crop classification and segmentation with deep learning

Contact Info

Product

Resources

About