Authors:
Emna Guermazi
1
;
2
;
3
;
Afef Mdhaffar
3
;
1
;
Mohamed Jmaiel
3
;
1
and
Bernd Freisleben
4
Affiliations:
1
ReDCAD Laboratory, ENIS, University of Sfax, B. P. 1173 Sfax, Tunisia
;
2
National School of Electronics and Telecommunications of Sfax, University of Sfax, 3018 Sfax, Tunisia
;
3
Digital Research Center of Sfax, 3021 Sfax, Tunisia
;
4
Department of Mathematics and Computer Science, Philipps-Universität, Marburg, Germany
Keyword(s):
Olive Disease Detection, Knowledge Distillation, Incremental Learning.
Abstract:
We present LIDL4Oliv, a novel lightweight incremental deep learning model for classifying olive diseases in images. LIDL4Oliv is first trained on a novel annotated dataset of images with complex background. Then, it learns from a large-scale deep learning model, following a knowledge distillation approach. Finally, LIDL4Oliv is successfully deployed as a cross-platform application on resource-limited mobile devices, such as smartphones. The deployed deep learning can detect olive leaves in images and classify their states as healthy or unhealthy, i.e., affected by one of the two diseases “Aculus Olearius” and “Peacock Spot”. Our mobile application supports the collection of real data during operation, i.e., the training dataset is continuously augmented by newly collected images of olive leaves. Furthermore, our deep learning model is retrained in a continuous manner, whenever a new set of data is collected. LIDL4Oliv follows an incremental update process. It does not ignore the know
ledge of the previously deployed model, but it (1) incorporates the current weights of the deployed model and (2) employs fine-tuning and knowledge distillation to create an enhanced incremental lightweight deep learning model. Our conducted experiments show the impact of using our complex background dataset to improve the classification results. They demonstrate the effect of using knowledge distillation in enhancing the performance of the deployed model on resource-limited devices.
(More)