A new hierarchical algorithm based on CapsGAN for imbalanced image classification
Abstract Imbalanced image datasets consist of image datasets where there is a significant disparity in the number of samples across different classes. With imbalanced image datasets, learning algorithms often tend to be biased toward the majority class samples. This leads to poor classification of m...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2024-01-01
|
| Series: | IET Image Processing |
| Subjects: | |
| Online Access: | https://doi.org/10.1049/ipr2.12942 |
| _version_ | 1797367525065883648 |
|---|---|
| author | Hamed Jabbari Nooshin Bigdeli |
| author_facet | Hamed Jabbari Nooshin Bigdeli |
| author_sort | Hamed Jabbari |
| collection | DOAJ |
| description | Abstract Imbalanced image datasets consist of image datasets where there is a significant disparity in the number of samples across different classes. With imbalanced image datasets, learning algorithms often tend to be biased toward the majority class samples. This leads to poor classification of minority class samples as their training is not properly conducted. It becomes more complicated when the number of samples in the minority class is very low. In this paper, a novel hierarchical algorithm is proposed for generating new data using Capsule Generative Adversarial Networks (CapsGAN) to address the class imbalance problem in imbalanced image datasets. Unlike common GAN models, the proposed method incorporates an auxiliary CapsNet to identify high‐value images in both minority and majority classes. This identification is based on the ability to detect complex relationships between low‐level and high‐level features present in capsule networks. Furthermore, the proposed CapsGAN model is conditioned to generate minority class samples based on feature vectors of last capsule layer to achieve a more balanced image dataset. For evaluating the performance of the proposed model, an image dataset called CICS was collected and introduced. Extensive experiments were also conducted using various online image datasets from different domains, with varying numbers of classes and data sizes. The experimental results demonstrated that the proposed model can generate high‐quality samples in cases where the image dataset or the number of minority class samples is relatively small. Furthermore, the proposed model has maintained an accuracy of over 80% in an imbalanced ratio of 1:60. |
| first_indexed | 2024-03-08T17:19:35Z |
| format | Article |
| id | doaj.art-228b41f32cd345e2876ccb19334ad92c |
| institution | Directory Open Access Journal |
| issn | 1751-9659 1751-9667 |
| language | English |
| last_indexed | 2024-03-08T17:19:35Z |
| publishDate | 2024-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | IET Image Processing |
| spelling | doaj.art-228b41f32cd345e2876ccb19334ad92c2024-01-03T07:39:13ZengWileyIET Image Processing1751-96591751-96672024-01-0118119421010.1049/ipr2.12942A new hierarchical algorithm based on CapsGAN for imbalanced image classificationHamed Jabbari0Nooshin Bigdeli1Department of Electrical Engineering Imam Khomeini International University Qazvin IranDepartment of Electrical Engineering Imam Khomeini International University Qazvin IranAbstract Imbalanced image datasets consist of image datasets where there is a significant disparity in the number of samples across different classes. With imbalanced image datasets, learning algorithms often tend to be biased toward the majority class samples. This leads to poor classification of minority class samples as their training is not properly conducted. It becomes more complicated when the number of samples in the minority class is very low. In this paper, a novel hierarchical algorithm is proposed for generating new data using Capsule Generative Adversarial Networks (CapsGAN) to address the class imbalance problem in imbalanced image datasets. Unlike common GAN models, the proposed method incorporates an auxiliary CapsNet to identify high‐value images in both minority and majority classes. This identification is based on the ability to detect complex relationships between low‐level and high‐level features present in capsule networks. Furthermore, the proposed CapsGAN model is conditioned to generate minority class samples based on feature vectors of last capsule layer to achieve a more balanced image dataset. For evaluating the performance of the proposed model, an image dataset called CICS was collected and introduced. Extensive experiments were also conducted using various online image datasets from different domains, with varying numbers of classes and data sizes. The experimental results demonstrated that the proposed model can generate high‐quality samples in cases where the image dataset or the number of minority class samples is relatively small. Furthermore, the proposed model has maintained an accuracy of over 80% in an imbalanced ratio of 1:60.https://doi.org/10.1049/ipr2.12942capsule networkdata augmentationdeep Learninggenerative adversarial networksimbalanced image classification |
| spellingShingle | Hamed Jabbari Nooshin Bigdeli A new hierarchical algorithm based on CapsGAN for imbalanced image classification IET Image Processing capsule network data augmentation deep Learning generative adversarial networks imbalanced image classification |
| title | A new hierarchical algorithm based on CapsGAN for imbalanced image classification |
| title_full | A new hierarchical algorithm based on CapsGAN for imbalanced image classification |
| title_fullStr | A new hierarchical algorithm based on CapsGAN for imbalanced image classification |
| title_full_unstemmed | A new hierarchical algorithm based on CapsGAN for imbalanced image classification |
| title_short | A new hierarchical algorithm based on CapsGAN for imbalanced image classification |
| title_sort | new hierarchical algorithm based on capsgan for imbalanced image classification |
| topic | capsule network data augmentation deep Learning generative adversarial networks imbalanced image classification |
| url | https://doi.org/10.1049/ipr2.12942 |
| work_keys_str_mv | AT hamedjabbari anewhierarchicalalgorithmbasedoncapsganforimbalancedimageclassification AT nooshinbigdeli anewhierarchicalalgorithmbasedoncapsganforimbalancedimageclassification AT hamedjabbari newhierarchicalalgorithmbasedoncapsganforimbalancedimageclassification AT nooshinbigdeli newhierarchicalalgorithmbasedoncapsganforimbalancedimageclassification |