Unsupervised multi-target domain adaptation for deforestation detection in tropical rainforest

Research output: Contribution to journalConference articleResearchpeer review

Authors

  • Mabel X. Ortega Adarme
  • Gilson A.O.P. da Costa
  • Pedro J. Soto Vega
  • Christian Heipke
  • Raul Q. Feitosa

External Research Organisations

  • Pontifícia Universidade Católica do Rio de Janeiro (PUC-Rio)
  • Universidade do Estado do Rio de Janeiro
View graph of relations

Details

Original languageEnglish
Pages (from-to)293-302
Number of pages10
JournalISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Volume X-3-2024
Publication statusPublished - 4 Nov 2024
Event2024 Symposium on Beyond the Canopy: Technologies and Applications of Remote Sensing - Belem, Brazil
Duration: 4 Nov 20248 Nov 2024

Abstract

Geographic variability of the classes of interest, differences in sensor characteristics and changes in atmospheric conditions during image acquisition, among other factors, make it challenging to use a pre-trained deep learning classifier on new remote sensing data without a substantial drop in classification accuracy. This phenomenon occurs due to the so-called domain shift problem. Deep domain adaptation techniques have been used to mitigate the problem and thus avoid the time-consuming and costly collection of new labeled samples. Most recent domain adaptation approaches rely on single-source and single-target domains, refraining from exploiting other data distributions that are usually available. This work introduces a new unsupervised multi-target domain adaptation in the context of a change detection application, namely deforestation detection. The proposed approach addresses the substantial class imbalance typical of such application by applying unsupervised algorithms for selecting pseudo-labels in the target domain that will later serve as additional training references. We report results of experiments to evaluate the proposed method in four distinct sites of two Brazilian biomes using Sentinel-2 images. The results indicate that the proposed unsupervised domain adaptation method is a promising solution to reduce the effects of domain shift and to deal with the scarcity of labeled training data.

Keywords

    Deforestation detection, domain adaptation, multi-target

ASJC Scopus subject areas

Cite this

Unsupervised multi-target domain adaptation for deforestation detection in tropical rainforest. / Ortega Adarme, Mabel X.; da Costa, Gilson A.O.P.; Soto Vega, Pedro J. et al.
In: ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, Vol. X-3-2024, 04.11.2024, p. 293-302.

Research output: Contribution to journalConference articleResearchpeer review

Ortega Adarme, MX, da Costa, GAOP, Soto Vega, PJ, Heipke, C & Feitosa, RQ 2024, 'Unsupervised multi-target domain adaptation for deforestation detection in tropical rainforest', ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, vol. X-3-2024, pp. 293-302. https://doi.org/10.5194/isprs-annals-X-3-2024-293-2024
Ortega Adarme, M. X., da Costa, G. A. O. P., Soto Vega, P. J., Heipke, C., & Feitosa, R. Q. (2024). Unsupervised multi-target domain adaptation for deforestation detection in tropical rainforest. ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, X-3-2024, 293-302. https://doi.org/10.5194/isprs-annals-X-3-2024-293-2024
Ortega Adarme MX, da Costa GAOP, Soto Vega PJ, Heipke C, Feitosa RQ. Unsupervised multi-target domain adaptation for deforestation detection in tropical rainforest. ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences. 2024 Nov 4; X-3-2024:293-302. doi: 10.5194/isprs-annals-X-3-2024-293-2024
Ortega Adarme, Mabel X. ; da Costa, Gilson A.O.P. ; Soto Vega, Pedro J. et al. / Unsupervised multi-target domain adaptation for deforestation detection in tropical rainforest. In: ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences. 2024 ; Vol. X-3-2024. pp. 293-302.
Download
@article{01ca659921e1414b8c22c965efffc193,
title = "Unsupervised multi-target domain adaptation for deforestation detection in tropical rainforest",
abstract = "Geographic variability of the classes of interest, differences in sensor characteristics and changes in atmospheric conditions during image acquisition, among other factors, make it challenging to use a pre-trained deep learning classifier on new remote sensing data without a substantial drop in classification accuracy. This phenomenon occurs due to the so-called domain shift problem. Deep domain adaptation techniques have been used to mitigate the problem and thus avoid the time-consuming and costly collection of new labeled samples. Most recent domain adaptation approaches rely on single-source and single-target domains, refraining from exploiting other data distributions that are usually available. This work introduces a new unsupervised multi-target domain adaptation in the context of a change detection application, namely deforestation detection. The proposed approach addresses the substantial class imbalance typical of such application by applying unsupervised algorithms for selecting pseudo-labels in the target domain that will later serve as additional training references. We report results of experiments to evaluate the proposed method in four distinct sites of two Brazilian biomes using Sentinel-2 images. The results indicate that the proposed unsupervised domain adaptation method is a promising solution to reduce the effects of domain shift and to deal with the scarcity of labeled training data.",
keywords = "Deforestation detection, domain adaptation, multi-target",
author = "{Ortega Adarme}, {Mabel X.} and {da Costa}, {Gilson A.O.P.} and {Soto Vega}, {Pedro J.} and Christian Heipke and Feitosa, {Raul Q.}",
note = "Publisher Copyright: {\textcopyright} Author(s) 2024.; 2024 Symposium on Beyond the Canopy: Technologies and Applications of Remote Sensing ; Conference date: 04-11-2024 Through 08-11-2024",
year = "2024",
month = nov,
day = "4",
doi = "10.5194/isprs-annals-X-3-2024-293-2024",
language = "English",
volume = " X-3-2024",
pages = "293--302",

}

Download

TY - JOUR

T1 - Unsupervised multi-target domain adaptation for deforestation detection in tropical rainforest

AU - Ortega Adarme, Mabel X.

AU - da Costa, Gilson A.O.P.

AU - Soto Vega, Pedro J.

AU - Heipke, Christian

AU - Feitosa, Raul Q.

N1 - Publisher Copyright: © Author(s) 2024.

PY - 2024/11/4

Y1 - 2024/11/4

N2 - Geographic variability of the classes of interest, differences in sensor characteristics and changes in atmospheric conditions during image acquisition, among other factors, make it challenging to use a pre-trained deep learning classifier on new remote sensing data without a substantial drop in classification accuracy. This phenomenon occurs due to the so-called domain shift problem. Deep domain adaptation techniques have been used to mitigate the problem and thus avoid the time-consuming and costly collection of new labeled samples. Most recent domain adaptation approaches rely on single-source and single-target domains, refraining from exploiting other data distributions that are usually available. This work introduces a new unsupervised multi-target domain adaptation in the context of a change detection application, namely deforestation detection. The proposed approach addresses the substantial class imbalance typical of such application by applying unsupervised algorithms for selecting pseudo-labels in the target domain that will later serve as additional training references. We report results of experiments to evaluate the proposed method in four distinct sites of two Brazilian biomes using Sentinel-2 images. The results indicate that the proposed unsupervised domain adaptation method is a promising solution to reduce the effects of domain shift and to deal with the scarcity of labeled training data.

AB - Geographic variability of the classes of interest, differences in sensor characteristics and changes in atmospheric conditions during image acquisition, among other factors, make it challenging to use a pre-trained deep learning classifier on new remote sensing data without a substantial drop in classification accuracy. This phenomenon occurs due to the so-called domain shift problem. Deep domain adaptation techniques have been used to mitigate the problem and thus avoid the time-consuming and costly collection of new labeled samples. Most recent domain adaptation approaches rely on single-source and single-target domains, refraining from exploiting other data distributions that are usually available. This work introduces a new unsupervised multi-target domain adaptation in the context of a change detection application, namely deforestation detection. The proposed approach addresses the substantial class imbalance typical of such application by applying unsupervised algorithms for selecting pseudo-labels in the target domain that will later serve as additional training references. We report results of experiments to evaluate the proposed method in four distinct sites of two Brazilian biomes using Sentinel-2 images. The results indicate that the proposed unsupervised domain adaptation method is a promising solution to reduce the effects of domain shift and to deal with the scarcity of labeled training data.

KW - Deforestation detection

KW - domain adaptation

KW - multi-target

UR - http://www.scopus.com/inward/record.url?scp=85212421812&partnerID=8YFLogxK

U2 - 10.5194/isprs-annals-X-3-2024-293-2024

DO - 10.5194/isprs-annals-X-3-2024-293-2024

M3 - Conference article

AN - SCOPUS:85212421812

VL - X-3-2024

SP - 293

EP - 302

JO - ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences

JF - ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences

SN - 2194-9042

T2 - 2024 Symposium on Beyond the Canopy: Technologies and Applications of Remote Sensing

Y2 - 4 November 2024 through 8 November 2024

ER -