Enhancing Image Classification in Small and Unbalanced Datasets through Synthetic Data Augmentation
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866916416909737984 |
|---|---|
| author | De La Fuente, Neil Majó, Mireia Luzko, Irina Córdova, Henry Fernández-Esparrach, Gloria Bernal, Jorge |
| author_facet | De La Fuente, Neil Majó, Mireia Luzko, Irina Córdova, Henry Fernández-Esparrach, Gloria Bernal, Jorge |
| contents | Accurate and robust medical image classification is a challenging task, especially in application domains where available annotated datasets are small and present high imbalance between target classes. Considering that data acquisition is not always feasible, especially for underrepresented classes, our approach introduces a novel synthetic augmentation strategy using class-specific Variational Autoencoders (VAEs) and latent space interpolation to improve discrimination capabilities.
By generating realistic, varied synthetic data that fills feature space gaps, we address issues of data scarcity and class imbalance. The method presented in this paper relies on the interpolation of latent representations within each class, thus enriching the training set and improving the model's generalizability and diagnostic accuracy. The proposed strategy was tested in a small dataset of 321 images created to train and validate an automatic method for assessing the quality of cleanliness of esophagogastroduodenoscopy images. By combining real and synthetic data, an increase of over 18\% in the accuracy of the most challenging underrepresented class was observed. The proposed strategy not only benefited the underrepresented class but also led to a general improvement in other metrics, including a 6\% increase in global accuracy and precision. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_10286 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Enhancing Image Classification in Small and Unbalanced Datasets through Synthetic Data Augmentation De La Fuente, Neil Majó, Mireia Luzko, Irina Córdova, Henry Fernández-Esparrach, Gloria Bernal, Jorge Computer Vision and Pattern Recognition Machine Learning Accurate and robust medical image classification is a challenging task, especially in application domains where available annotated datasets are small and present high imbalance between target classes. Considering that data acquisition is not always feasible, especially for underrepresented classes, our approach introduces a novel synthetic augmentation strategy using class-specific Variational Autoencoders (VAEs) and latent space interpolation to improve discrimination capabilities. By generating realistic, varied synthetic data that fills feature space gaps, we address issues of data scarcity and class imbalance. The method presented in this paper relies on the interpolation of latent representations within each class, thus enriching the training set and improving the model's generalizability and diagnostic accuracy. The proposed strategy was tested in a small dataset of 321 images created to train and validate an automatic method for assessing the quality of cleanliness of esophagogastroduodenoscopy images. By combining real and synthetic data, an increase of over 18\% in the accuracy of the most challenging underrepresented class was observed. The proposed strategy not only benefited the underrepresented class but also led to a general improvement in other metrics, including a 6\% increase in global accuracy and precision. |
| title | Enhancing Image Classification in Small and Unbalanced Datasets through Synthetic Data Augmentation |
| topic | Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2409.10286 |