Explainable Deep Learning to Classify Royal Navy Ships
Explainable Deep Learning to Classify Royal Navy Ships
We research how deep learning convolutional neural networks can be used to automatically classify the unique data set of black-and-white naval ships images from the Wright and Logan photographic collection held by the National Museum of the Royal Navy. We contrast various types of deep learning methods: pretrained models such as ConvNeXt, ResNet and EfficientNet, and ConvMixer. We also thoroughly investigate the impact of data preprocessing and externally obtained images on model performance. Finally, we research how the models estimated can be made transparent using visually appealing interpretability techniques such as Grad-CAM. We find that ConvNeXt has the best performance for our data set achieving an accuracy of 79.62% for 0-notch classification and an impressive 94.86% for 1-notch classification. The results indicate the importance of appropriate image preprocessing. Image segmentation combined with soft augmentation significantly contributes to model performance. We consider this research to be original in several aspects. Notably, it distinguishes itself through the uniqueness of the acquired dataset. Additionally, its distinctiveness extends to the analytical modeling pipeline, which encompasses a comprehensive range of modeling steps, including data preprocessing (incorporating external data, image segmentation, and image augmentation) and the use of deep learning techniques such as ConvNeXt, ResNet, EfficientNet, and ConvMixer. Furthermore, the research employs explanatory tools like Grad-CAM to enhance model interpretability and usability. We believe the proposed methodology offers lots of potential for documenting historic image collections.
Convolutional Neural Networks, Convolutional neural networks, Deep Learning, Deep learning, Digitised Archives, Documentation, Explainability, Image Classification, Labeling, Marine vehicles, Modeling, Museums, Royal Navy, royal navy, explainability, image classification, deep learning, digitised archives
1774-1785
Baesens, Bart
f7c6496b-aa7f-4026-8616-ca61d9e216f0
Adams, Amy
222cd26a-7833-4dab-984e-4102c9d74f02
Pacheco-Ruiz, Rodrigo
5966635c-eca5-4852-8f73-3b5b00e3b7ec
Baesens, Ann-Sophie
2c881a45-fe58-4fb6-8233-22dc5a4937cc
Vanden Broucke, Seppe
89c69367-232e-4c1e-9e57-531bf474e12d
2024
Baesens, Bart
f7c6496b-aa7f-4026-8616-ca61d9e216f0
Adams, Amy
222cd26a-7833-4dab-984e-4102c9d74f02
Pacheco-Ruiz, Rodrigo
5966635c-eca5-4852-8f73-3b5b00e3b7ec
Baesens, Ann-Sophie
2c881a45-fe58-4fb6-8233-22dc5a4937cc
Vanden Broucke, Seppe
89c69367-232e-4c1e-9e57-531bf474e12d
Baesens, Bart, Adams, Amy, Pacheco-Ruiz, Rodrigo, Baesens, Ann-Sophie and Vanden Broucke, Seppe
(2024)
Explainable Deep Learning to Classify Royal Navy Ships.
IEEE Access, 12, .
(doi:10.1109/ACCESS.2023.3346061).
Abstract
We research how deep learning convolutional neural networks can be used to automatically classify the unique data set of black-and-white naval ships images from the Wright and Logan photographic collection held by the National Museum of the Royal Navy. We contrast various types of deep learning methods: pretrained models such as ConvNeXt, ResNet and EfficientNet, and ConvMixer. We also thoroughly investigate the impact of data preprocessing and externally obtained images on model performance. Finally, we research how the models estimated can be made transparent using visually appealing interpretability techniques such as Grad-CAM. We find that ConvNeXt has the best performance for our data set achieving an accuracy of 79.62% for 0-notch classification and an impressive 94.86% for 1-notch classification. The results indicate the importance of appropriate image preprocessing. Image segmentation combined with soft augmentation significantly contributes to model performance. We consider this research to be original in several aspects. Notably, it distinguishes itself through the uniqueness of the acquired dataset. Additionally, its distinctiveness extends to the analytical modeling pipeline, which encompasses a comprehensive range of modeling steps, including data preprocessing (incorporating external data, image segmentation, and image augmentation) and the use of deep learning techniques such as ConvNeXt, ResNet, EfficientNet, and ConvMixer. Furthermore, the research employs explanatory tools like Grad-CAM to enhance model interpretability and usability. We believe the proposed methodology offers lots of potential for documenting historic image collections.
Text
Royal_Navy_IEEE_Access_Baesens
- Accepted Manuscript
More information
Accepted/In Press date: 15 December 2023
e-pub ahead of print date: 22 December 2023
Published date: 2024
Additional Information:
Publisher Copyright:
© 2013 IEEE.
Keywords:
Convolutional Neural Networks, Convolutional neural networks, Deep Learning, Deep learning, Digitised Archives, Documentation, Explainability, Image Classification, Labeling, Marine vehicles, Modeling, Museums, Royal Navy, royal navy, explainability, image classification, deep learning, digitised archives
Identifiers
Local EPrints ID: 485960
URI: http://eprints.soton.ac.uk/id/eprint/485960
ISSN: 2169-3536
PURE UUID: 1ca89786-6c80-453f-8d73-7666d85fa738
Catalogue record
Date deposited: 04 Jan 2024 06:19
Last modified: 18 Mar 2024 02:59
Export record
Altmetrics
Contributors
Author:
Amy Adams
Author:
Ann-Sophie Baesens
Author:
Seppe Vanden Broucke
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics
