Unknown Landscape Identification with CNN Transfer Learning

Serra, Edoardo; Sharma, Ashish; Joaristi, Mikel; Korzh, Oxana

doi:10.1109/asonam.2018.8508357

Cited by 11 publications

(2 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Two attributes are important to help the transfer (28): (i) The success of the pretrained model can promote the exclusion of user intervention with the boring hyper-parameter tuning of new tasks; (ii) The early layers in pretrained models can be determined as feature extractors that help to extract low-level features, such as edges, tints, shades, and textures.…”

Section: Methodsmentioning

confidence: 99%

Alcoholism Identification Based on an AlexNet Transfer Learning Model

et al. 2019

View full text Add to dashboard Cite

Aim: This paper proposes a novel alcoholism identification approach that can assist radiologists in patient diagnosis. Method: AlexNet was used as the basic transfer learning model. The global learning rate was small, at 10 −4 , and the iteration epoch number was at 10. The learning rate factor of replaced layers was 10 times larger than that of the transferred layers. We tested five different replacement configurations of transfer learning. Results: The experiment shows that the best performance was achieved by replacing the final fully connected layer. Our method yielded a sensitivity of 97.44%± 1.15%, a specificity of 97.41 ± 1.51%, a precision of 97.34 ± 1.49%, an accuracy of 97.42 ± 0.95%, and an F1 score of 97.37 ± 0.97% on the test set. Conclusion: This method can assist radiologists in their routine alcoholism screening of brain magnetic resonance images.

show abstract

Section: Methodsmentioning

confidence: 99%

Alcoholism Identification Based on an AlexNet Transfer Learning Model

et al. 2019

View full text Add to dashboard Cite

show abstract

“…TL is commonly used when training a small dataset where the CNN's weights are initialized before being fine-tuned with the new dataset [19]. TL aids in adapting current models trained on large datasets to work in a specific context [20]. There are several pre-trained models approaches based on this research, including VGG16, ResNet-50, Xception and DenseNet121.…”

Section: Transfer Learningmentioning

confidence: 99%

An Efficient Approach Based on Privacy-Preserving Deep Learning for Satellite Image Classification

et al. 2021

View full text Add to dashboard Cite

Satellite images have drawn increasing interest from a wide variety of users, including business and government, ever since their increased usage in important fields ranging from weather, forestry and agriculture to surface changes and biodiversity monitoring. Recent updates in the field have also introduced various deep learning (DL) architectures to satellite imagery as a means of extracting useful information. However, this new approach comes with its own issues, including the fact that many users utilize ready-made cloud services (both public and private) in order to take advantage of built-in DL algorithms and thus avoid the complexity of developing their own DL architectures. However, this presents new challenges to protecting data against unauthorized access, mining and usage of sensitive information extracted from that data. Therefore, new privacy concerns regarding sensitive data in satellite images have arisen. This research proposes an efficient approach that takes advantage of privacy-preserving deep learning (PPDL)-based techniques to address privacy concerns regarding data from satellite images when applying public DL models. In this paper, we proposed a partially homomorphic encryption scheme (a Paillier scheme), which enables processing of confidential information without exposure of the underlying data. Our method achieves robust results when applied to a custom convolutional neural network (CNN) as well as to existing transfer learning methods. The proposed encryption scheme also allows for training CNN models on encrypted data directly, which requires lower computational overhead. Our experiments have been performed on a real-world dataset covering several regions across Saudi Arabia. The results demonstrate that our CNN-based models were able to retain data utility while maintaining data privacy. Security parameters such as correlation coefficient (−0.004), entropy (7.95), energy (0.01), contrast (10.57), number of pixel change rate (4.86), unified average change intensity (33.66), and more are in favor of our proposed encryption scheme. To the best of our knowledge, this research is also one of the first studies that applies PPDL-based techniques to satellite image data in any capacity.

show abstract