TimeMatch: Unsupervised cross-region adaptation by temporal shift estimation

Nyborg, Joachim; Pelletier, Charlotte; Lefèvre, Sébastien; Assent, Ira

doi:10.1016/j.isprsjprs.2022.04.018

Cited by 31 publications

(17 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The choice of augmentation provides several opportunities to learn a better representation that could also be invariant to regional differences. For example, Nyborg et al (2021) introduced the temporal shift of crop time series in different regions which inspired us to use a drift (Aug2) as augmentation. However, this was only partially successful in learning a shift-invariant representation.…”

Section: Discussionmentioning

confidence: 99%

Self-supervised learning -- A way to minimize time and effort for precision agriculture?

Marszalek¹,

Saux²,

Mathieu³

et al. 2022

Preprint

View full text Add to dashboard Cite

Machine learning, satellites or local sensors are key factors for a sustainable and resource-saving optimisation of agriculture and proved its values for the management of agricultural land. Up to now, the main focus was on the enlargement of data which were evaluated by means of supervised learning methods. Nevertheless, the need for labels is also a limiting and time-consuming factor, while in contrast, ongoing technological development is already providing an ever-increasing amount of unlabeled data. Self-supervised learning (SSL) could overcome this limitation and incorporate existing unlabeled data. Therefore, a crop type data set was utilized to conduct experiments with SSL and compare it to supervised methods. A unique feature of our data set from 2016 to 2018 was a divergent climatological condition in 2018 that reduced yields and affected the spectral fingerprint of the plants. Our experiments focused on predicting 2018 using SLL without or a few labels to clarify whether new labels should be collected for an unknown year. Despite these challenging conditions, the results showed that SSL contributed to higher accuracies. We believe that the results will encourage further improvements in the field of precision farming, why the SSL framework and data will be published (Marszalek, 2021).

show abstract

Section: Discussionmentioning

confidence: 99%

Self-supervised learning -- A way to minimize time and effort for precision agriculture?

Marszalek¹,

Saux²,

Mathieu³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Concerning the remote sensing field, early research focused on proposing UDA strategies for high spatial resolution images [44], while only recently some strategies are emerging in the context of satellite image time series [11]. More generally, in this context distribution shifts between training (source) and test (target) data can be induced by different factors, and among others, differences in sensor acquisitions and environmental conditions are the most recurrent ones.…”

Section: Unsupervised Domain Adaptationmentioning

confidence: 99%

“…We here start from the observation that directly transfer a model trained on a particular year (the source domain) to a successive period of time (the target domain) can be challenging since the two time periods can be affected by different environmental, weather or climate conditions [10], [11]. This results in differences or shifts in the distributions of the acquired yearly remote sensing data.…”

Section: Introductionmentioning

confidence: 99%

Temporal-Domain Adaptation for Satellite Image Time-Series Land-Cover Mapping With Adversarial Learning and Spatially Aware Self-Training

Capliez

Ienco

Gaetano

et al. 2023

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

View full text Add to dashboard Cite

“…Lucas et al (2020) conduct experiments on Satelite Image Time Series (SITS) classification using existing natural image-based UDA methods and find that those UDA methods are ineffective, due to the temporal nature of SITS. Nyborg et al (2022) propose an explicit UDA method that learns the temporal shift of SITS for crop classification and introduce a dataset for cross-region adaptation from SITS in four different regions in Europe. Ma and Zhang (2021) introduce a UDA approach for corn-yield prediction using time-series vegetation indices and weather observations.…”

Section: Climate Science and Geosciencesmentioning

confidence: 99%

Deep Unsupervised Domain Adaptation: A Review of Recent Advances and Perspectives

Liu

Yoo

Xing

et al. 2022

SIP

113

View full text Add to dashboard Cite

Deep learning has become the method of choice to tackle real-world problems in different domains, partly because of its ability to learn from data and achieve impressive performance on a wide range of applications. However, its success usually relies on two assumptions: (i) vast troves of labeled datasets are required for accurate model fitting, and (ii) training and testing data are independent and identically distributed. Its performance on unseen target domains, thus, is not guaranteed, especially when encountering out-of-distribution data at the adaptation stage. The performance drop on data in a target domain is a critical problem in deploying deep neural networks that are successfully trained on data in a source domain. Unsupervised domain adaptation (UDA) is proposed to counter this, by leveraging both labeled source domain data and unlabeled target domain data to carry out various tasks in the target domain. UDA has yielded promising results on natural image processing, video analysis, natural language processing, time-series data analysis, medical image analysis, etc. In this review, as a rapidly evolving topic, we provide a systematic comparison of its methods and applications. In addition, the connection of UDA with its closely related tasks, e.g., domain generalization and out-of-distribution detection, has also been discussed. Furthermore, deficiencies in current methods and possible promising directions are highlighted.

show abstract

TimeMatch: Unsupervised cross-region adaptation by temporal shift estimation

Cited by 31 publications

References 21 publications

Self-supervised learning -- A way to minimize time and effort for precision agriculture?

Self-supervised learning -- A way to minimize time and effort for precision agriculture?

Temporal-Domain Adaptation for Satellite Image Time-Series Land-Cover Mapping With Adversarial Learning and Spatially Aware Self-Training

Deep Unsupervised Domain Adaptation: A Review of Recent Advances and Perspectives

Contact Info

Product

Resources

About