Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2406.17473 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911932087271424 |
|---|---|
| author | Niemeijer, Joshua Ehrhardt, Jan Uzunova, Hristina Handels, Heinz |
| author_facet | Niemeijer, Joshua Ehrhardt, Jan Uzunova, Hristina Handels, Heinz |
| contents | The usage of medical image data for the training of large-scale machine learning approaches is particularly challenging due to its scarce availability and the costly generation of data annotations, typically requiring the engagement of medical professionals. The rapid development of generative models allows towards tackling this problem by leveraging large amounts of realistic synthetically generated data for the training process. However, randomly choosing synthetic samples, might not be an optimal strategy.
In this work, we investigate the targeted generation of synthetic training data, in order to improve the accuracy and robustness of image classification. Therefore, our approach aims to guide the generative model to synthesize data with high epistemic uncertainty, since large measures of epistemic uncertainty indicate underrepresented data points in the training set. During the image generation we feed images reconstructed by an auto encoder into the classifier and compute the mutual information over the class-probability distribution as a measure for uncertainty.We alter the feature space of the autoencoder through an optimization process with the objective of maximizing the classifier uncertainty on the decoded image. By training on such data we improve the performance and robustness against test time data augmentations and adversarial attacks on several classifications tasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_17473 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | TSynD: Targeted Synthetic Data Generation for Enhanced Medical Image Classification Niemeijer, Joshua Ehrhardt, Jan Uzunova, Hristina Handels, Heinz Computer Vision and Pattern Recognition Artificial Intelligence The usage of medical image data for the training of large-scale machine learning approaches is particularly challenging due to its scarce availability and the costly generation of data annotations, typically requiring the engagement of medical professionals. The rapid development of generative models allows towards tackling this problem by leveraging large amounts of realistic synthetically generated data for the training process. However, randomly choosing synthetic samples, might not be an optimal strategy. In this work, we investigate the targeted generation of synthetic training data, in order to improve the accuracy and robustness of image classification. Therefore, our approach aims to guide the generative model to synthesize data with high epistemic uncertainty, since large measures of epistemic uncertainty indicate underrepresented data points in the training set. During the image generation we feed images reconstructed by an auto encoder into the classifier and compute the mutual information over the class-probability distribution as a measure for uncertainty.We alter the feature space of the autoencoder through an optimization process with the objective of maximizing the classifier uncertainty on the decoded image. By training on such data we improve the performance and robustness against test time data augmentations and adversarial attacks on several classifications tasks. |
| title | TSynD: Targeted Synthetic Data Generation for Enhanced Medical Image Classification |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2406.17473 |