Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2405.20987 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914817880621056 |
|---|---|
| author | Saad, Muhammad Muneeb Rehmani, Mubashir Husain O'Reilly, Ruairi |
| author_facet | Saad, Muhammad Muneeb Rehmani, Mubashir Husain O'Reilly, Ruairi |
| contents | Generative Adversarial Networks (GANs) have high computational costs to train their complex architectures. Throughout the training process, GANs' output is analyzed qualitatively based on the loss and synthetic images' diversity and quality. Based on this qualitative analysis, training is manually halted once the desired synthetic images are generated. By utilizing an early stopping criterion, the computational cost and dependence on manual oversight can be reduced yet impacted by training problems such as mode collapse, non-convergence, and instability. This is particularly prevalent in biomedical imagery, where training problems degrade the diversity and quality of synthetic images, and the high computational cost associated with training makes complex architectures increasingly inaccessible. This work proposes a novel early stopping criteria to quantitatively detect training problems, halt training, and reduce the computational costs associated with synthesizing biomedical images. Firstly, the range of generator and discriminator loss values is investigated to assess whether mode collapse, non-convergence, and instability occur sequentially, concurrently, or interchangeably throughout the training of GANs. Secondly, utilizing these occurrences in conjunction with the Mean Structural Similarity Index (MS-SSIM) and Fréchet Inception Distance (FID) scores of synthetic images forms the basis of the proposed early stopping criteria. This work helps identify the occurrence of training problems in GANs using low-resource computational cost and reduces training time to generate diversified and high-quality synthetic images. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_20987 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Early Stopping Criteria for Training Generative Adversarial Networks in Biomedical Imaging Saad, Muhammad Muneeb Rehmani, Mubashir Husain O'Reilly, Ruairi Computer Vision and Pattern Recognition Machine Learning Image and Video Processing Generative Adversarial Networks (GANs) have high computational costs to train their complex architectures. Throughout the training process, GANs' output is analyzed qualitatively based on the loss and synthetic images' diversity and quality. Based on this qualitative analysis, training is manually halted once the desired synthetic images are generated. By utilizing an early stopping criterion, the computational cost and dependence on manual oversight can be reduced yet impacted by training problems such as mode collapse, non-convergence, and instability. This is particularly prevalent in biomedical imagery, where training problems degrade the diversity and quality of synthetic images, and the high computational cost associated with training makes complex architectures increasingly inaccessible. This work proposes a novel early stopping criteria to quantitatively detect training problems, halt training, and reduce the computational costs associated with synthesizing biomedical images. Firstly, the range of generator and discriminator loss values is investigated to assess whether mode collapse, non-convergence, and instability occur sequentially, concurrently, or interchangeably throughout the training of GANs. Secondly, utilizing these occurrences in conjunction with the Mean Structural Similarity Index (MS-SSIM) and Fréchet Inception Distance (FID) scores of synthetic images forms the basis of the proposed early stopping criteria. This work helps identify the occurrence of training problems in GANs using low-resource computational cost and reduces training time to generate diversified and high-quality synthetic images. |
| title | Early Stopping Criteria for Training Generative Adversarial Networks in Biomedical Imaging |
| topic | Computer Vision and Pattern Recognition Machine Learning Image and Video Processing |
| url | https://arxiv.org/abs/2405.20987 |