Details
Originalsprache | Englisch |
---|---|
Aufsatznummer | 3431 |
Seitenumfang | 17 |
Fachzeitschrift | Remote sensing |
Jahrgang | 12 |
Ausgabenummer | 20 |
Publikationsstatus | Veröffentlicht - 19 Okt. 2020 |
Abstract
Deep Learning (DL) has become popular due to its ease of use and accuracy, with Transfer Learning (TL) effectively reducing the number of images needed to solve environmental problems. However, this approach has some limitations which we set out to explore: Our goal is to detect the presence of an invasive blueberry species in aerial images of wetlands. This is a key problem in ecosystem protection which is also challenging in terms of DL due to the severe imbalance present in the data. Results for the ResNet50 network show a high classification accuracy while largely ignoring the blueberry class, rendering these results of limited practical interest to detect that specific class. Moreover, by using loss function weighting and data augmentation results more akin to our practical application, our goals can be obtained. Our experiments regarding TL show that ImageNet weights do not produce satisfactory results when only the final layer of the network is trained. Furthermore, only minor gains are obtained compared with random weights when the whole network is retrained. Finally, in a study of state-of-the-art DL architectures best results were obtained by the ResNeXt architecture with 93.75 True Positive Rate and 98.11 accuracy for the Blueberry class with ResNet50, Densenet, and wideResNet obtaining close results.
ASJC Scopus Sachgebiete
Zitieren
- Standard
- Harvard
- Apa
- Vancouver
- BibTex
- RIS
in: Remote sensing, Jahrgang 12, Nr. 20, 3431, 19.10.2020.
Publikation: Beitrag in Fachzeitschrift › Artikel › Forschung › Peer-Review
}
TY - JOUR
T1 - Detection of Invasive Species in Wetlands: Practical DL with Heavily Imbalanced Data
AU - Cabezas, Mariano
AU - Kentsch, Sarah
AU - Tomhave, Luca
AU - Gross, Jens
AU - Caceres, Maximo Larry Lopez
AU - Diez, Yago
PY - 2020/10/19
Y1 - 2020/10/19
N2 - Deep Learning (DL) has become popular due to its ease of use and accuracy, with Transfer Learning (TL) effectively reducing the number of images needed to solve environmental problems. However, this approach has some limitations which we set out to explore: Our goal is to detect the presence of an invasive blueberry species in aerial images of wetlands. This is a key problem in ecosystem protection which is also challenging in terms of DL due to the severe imbalance present in the data. Results for the ResNet50 network show a high classification accuracy while largely ignoring the blueberry class, rendering these results of limited practical interest to detect that specific class. Moreover, by using loss function weighting and data augmentation results more akin to our practical application, our goals can be obtained. Our experiments regarding TL show that ImageNet weights do not produce satisfactory results when only the final layer of the network is trained. Furthermore, only minor gains are obtained compared with random weights when the whole network is retrained. Finally, in a study of state-of-the-art DL architectures best results were obtained by the ResNeXt architecture with 93.75 True Positive Rate and 98.11 accuracy for the Blueberry class with ResNet50, Densenet, and wideResNet obtaining close results.
AB - Deep Learning (DL) has become popular due to its ease of use and accuracy, with Transfer Learning (TL) effectively reducing the number of images needed to solve environmental problems. However, this approach has some limitations which we set out to explore: Our goal is to detect the presence of an invasive blueberry species in aerial images of wetlands. This is a key problem in ecosystem protection which is also challenging in terms of DL due to the severe imbalance present in the data. Results for the ResNet50 network show a high classification accuracy while largely ignoring the blueberry class, rendering these results of limited practical interest to detect that specific class. Moreover, by using loss function weighting and data augmentation results more akin to our practical application, our goals can be obtained. Our experiments regarding TL show that ImageNet weights do not produce satisfactory results when only the final layer of the network is trained. Furthermore, only minor gains are obtained compared with random weights when the whole network is retrained. Finally, in a study of state-of-the-art DL architectures best results were obtained by the ResNeXt architecture with 93.75 True Positive Rate and 98.11 accuracy for the Blueberry class with ResNet50, Densenet, and wideResNet obtaining close results.
KW - Data analysis
KW - Deep learning
KW - Transfer learning
KW - Unbalanced data
KW - Unmanned aerial vehicles (UAV)-acquired images
UR - http://www.scopus.com/inward/record.url?scp=85092778376&partnerID=8YFLogxK
U2 - 10.3390/rs12203431
DO - 10.3390/rs12203431
M3 - Article
VL - 12
JO - Remote sensing
JF - Remote sensing
SN - 2072-4292
IS - 20
M1 - 3431
ER -