Enhancing Deep Learning Model Robustness through Metamorphic Re-Training
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_ | 1866913595312308224 |
|---|---|
| author | Togru, Said Mostafa, Youssef Sameh Lotfy, Karim |
| author_facet | Togru, Said Mostafa, Youssef Sameh Lotfy, Karim |
| contents | This paper evaluates the use of metamorphic relations to enhance the robustness and real-world performance of machine learning models. We propose a Metamorphic Retraining Framework, which applies metamorphic relations to data and utilizes semi-supervised learning algorithms in an iterative and adaptive multi-cycle process. The framework integrates multiple semi-supervised retraining algorithms, including FixMatch, FlexMatch, MixMatch, and FullMatch, to automate the retraining, evaluation, and testing of models with specified configurations. To assess the effectiveness of this approach, we conducted experiments on CIFAR-10, CIFAR-100, and MNIST datasets using a variety of image processing models, both pretrained and non-pretrained. Our results demonstrate the potential of metamorphic retraining to significantly improve model robustness as we show in our results that each model witnessed an increase of an additional flat 17 percent on average in our robustness metric. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_01958 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Enhancing Deep Learning Model Robustness through Metamorphic Re-Training Togru, Said Mostafa, Youssef Sameh Lotfy, Karim Computer Vision and Pattern Recognition Artificial Intelligence This paper evaluates the use of metamorphic relations to enhance the robustness and real-world performance of machine learning models. We propose a Metamorphic Retraining Framework, which applies metamorphic relations to data and utilizes semi-supervised learning algorithms in an iterative and adaptive multi-cycle process. The framework integrates multiple semi-supervised retraining algorithms, including FixMatch, FlexMatch, MixMatch, and FullMatch, to automate the retraining, evaluation, and testing of models with specified configurations. To assess the effectiveness of this approach, we conducted experiments on CIFAR-10, CIFAR-100, and MNIST datasets using a variety of image processing models, both pretrained and non-pretrained. Our results demonstrate the potential of metamorphic retraining to significantly improve model robustness as we show in our results that each model witnessed an increase of an additional flat 17 percent on average in our robustness metric. |
| title | Enhancing Deep Learning Model Robustness through Metamorphic Re-Training |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2412.01958 |