A Light-Weight Deep Learning Model for Remote Sensing Image Classification

In this paper, we present a high-performance and light-weight deep learning model for Remote Sensing Image Classification (RSIC), the task of identifying the aerial scene of a remote sensing image. To this end, we first evaluate various benchmark convolutional neural network (CNN) architectures: Mob...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:2023 International Symposium on Image and Signal Processing and Analysis (ISPA) S. 1 - 6
Hauptverfasser: Pham, Lam, Le, Cam, Ngo, Dat, Nguyen, Anh, Lampert, Jasmin, Schindler, Alexander, McLoughlin, Ian
Format: Tagungsbericht
Sprache:Englisch
Veröffentlicht: IEEE 18.09.2023
Schlagworte:
Analytical models
Benchmark testing
Complexity theory
Computational modeling
convolutional neural network (CNN)
Convolutional neural networks
data augmentation
Deep learning
high-level features
Image edge detection
Teacher-student model
ISSN:1849-2266
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:In this paper, we present a high-performance and light-weight deep learning model for Remote Sensing Image Classification (RSIC), the task of identifying the aerial scene of a remote sensing image. To this end, we first evaluate various benchmark convolutional neural network (CNN) architectures: MobileNet V1/V2, ResNet 50/151V2, InceptionV3/InceptionResNetV2, EfficientNet B0/B7, DenseNet 121/201, ConNeXt Tiny/Large. Then, the best performing models are selected to train a compact model in a teacher-student arrangement. The knowledge distillation from the teacher aims to achieve high performance with significantly reduced complexity. By conducting extensive experiments on the NWPU-RESISC45 benchmark, our proposed teacher and student models outper-forms the state-of-the-art systems, and has potential to be applied on a wide range of edge devices.
ISSN:1849-2266
DOI:10.1109/ISPA58351.2023.10279679