التفاصيل البيبلوغرافية
| العنوان: |
Using Segmentation to Boost Classification Performance and Explainability in CapsNets. |
| المؤلفون: |
Vranay, Dominik, Hliboký, Maroš, Kovács, László, Sinčák, Peter |
| المصدر: |
Machine Learning & Knowledge Extraction; Sep2024, Vol. 6 Issue 3, p1439-1465, 27p |
| مصطلحات موضوعية: |
CAPSULE neural networks, IMAGE recognition (Computer vision), FEATURE extraction, IMAGE reconstruction, ROUTING algorithms |
| مستخلص: |
In this paper, we present Combined-CapsNet (C-CapsNet), a novel approach aimed at enhancing the performance and explainability of Capsule Neural Networks (CapsNets) in image classification tasks. Our method involves the integration of segmentation masks as reconstruction targets within the CapsNet architecture. This integration helps in better feature extraction by focusing on significant image parts while reducing the number of parameters required for accurate classification. C-CapsNet combines principles from Efficient-CapsNet and the original CapsNet, introducing several novel improvements such as the use of segmentation masks to reconstruct images and a number of tweaks to the routing algorithm, which enhance both classification accuracy and interoperability. We evaluated C-CapsNet using the Oxford-IIIT Pet and SIIM-ACR Pneumothorax datasets, achieving mean F1 scores of 93% and 67%, respectively. These results demonstrate a significant performance improvement over traditional CapsNet and CNN models. The method's effectiveness is further highlighted by its ability to produce clear and interpretable segmentation masks, which can be used to validate the network's focus during classification tasks. Our findings suggest that C-CapsNet not only improves the accuracy of CapsNets but also enhances their explainability, making them more suitable for real-world applications, particularly in medical imaging. [ABSTRACT FROM AUTHOR] |
|
Copyright of Machine Learning & Knowledge Extraction is the property of MDPI and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) |
| قاعدة البيانات: |
Complementary Index |