Details
Original language | English |
---|---|
Pages (from-to) | 293-302 |
Number of pages | 10 |
Journal | ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences |
Volume | X-3-2024 |
Publication status | Published - 4 Nov 2024 |
Event | 2024 Symposium on Beyond the Canopy: Technologies and Applications of Remote Sensing - Belem, Brazil Duration: 4 Nov 2024 → 8 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
- Physics and Astronomy(all)
- Instrumentation
- Environmental Science(all)
- Environmental Science (miscellaneous)
- Earth and Planetary Sciences(all)
- Earth and Planetary Sciences (miscellaneous)
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
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 journal › Conference article › Research › peer review
}
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 -