Long Tail Image Generation Through Feature Space Augmentation and Iterated Learning
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_ | 1866916591237595136 |
|---|---|
| author | Elberg, Rafael Parra, Denis Petrache, Mircea |
| author_facet | Elberg, Rafael Parra, Denis Petrache, Mircea |
| contents | Image and multimodal machine learning tasks are very challenging to solve in the case of poorly distributed data. In particular, data availability and privacy restrictions exacerbate these hurdles in the medical domain. The state of the art in image generation quality is held by Latent Diffusion models, making them prime candidates for tackling this problem. However, a few key issues still need to be solved, such as the difficulty in generating data from under-represented classes and a slow inference process. To mitigate these issues, we propose a new method for image augmentation in long-tailed data based on leveraging the rich latent space of pre-trained Stable Diffusion Models. We create a modified separable latent space to mix head and tail class examples. We build this space via Iterated Learning of underlying sparsified embeddings, which we apply to task-specific saliency maps via a K-NN approach. Code is available at https://github.com/SugarFreeManatee/Feature-Space-Augmentation-and-Iterated-Learning |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_01705 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Long Tail Image Generation Through Feature Space Augmentation and Iterated Learning Elberg, Rafael Parra, Denis Petrache, Mircea Computer Vision and Pattern Recognition Artificial Intelligence I.4; I.2 Image and multimodal machine learning tasks are very challenging to solve in the case of poorly distributed data. In particular, data availability and privacy restrictions exacerbate these hurdles in the medical domain. The state of the art in image generation quality is held by Latent Diffusion models, making them prime candidates for tackling this problem. However, a few key issues still need to be solved, such as the difficulty in generating data from under-represented classes and a slow inference process. To mitigate these issues, we propose a new method for image augmentation in long-tailed data based on leveraging the rich latent space of pre-trained Stable Diffusion Models. We create a modified separable latent space to mix head and tail class examples. We build this space via Iterated Learning of underlying sparsified embeddings, which we apply to task-specific saliency maps via a K-NN approach. Code is available at https://github.com/SugarFreeManatee/Feature-Space-Augmentation-and-Iterated-Learning |
| title | Long Tail Image Generation Through Feature Space Augmentation and Iterated Learning |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence I.4; I.2 |
| url | https://arxiv.org/abs/2405.01705 |