Guardado en:
Detalles Bibliográficos
Autores principales: Doherty, William, Lee, Anton, Gomes, Heitor Murilo
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:https://arxiv.org/abs/2501.11140
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866912194193522688
author Doherty, William
Lee, Anton
Gomes, Heitor Murilo
author_facet Doherty, William
Lee, Anton
Gomes, Heitor Murilo
contents The rapid advancement of generative AI models capable of creating realistic media has led to a need for classifiers that can accurately distinguish between genuine and artificially-generated images. A significant challenge for these classifiers emerges when they encounter images from generative models that are not represented in their training data, usually resulting in diminished performance. A typical approach is to periodically update the classifier's training data with images from the new generative models then retrain the classifier on the updated dataset. However, in some real-life scenarios, storage, computational, or privacy constraints render this approach impractical. Additionally, models used in security applications may be required to rapidly adapt. In these circumstances, continual learning provides a promising alternative, as the classifier can be updated without retraining on the entire dataset. In this paper, we introduce a new dataset called CLOFAI (Continual Learning On Fake and Authentic Images), which takes the form of a domain-incremental image classification problem. Moreover, we showcase the applicability of this dataset as a benchmark for evaluating continual learning methodologies. In doing this, we set a baseline on our novel dataset using three foundational continual learning methods -- EWC, GEM, and Experience Replay -- and find that EWC performs poorly, while GEM and Experience Replay show promise, performing significantly better than a Naive baseline. The dataset and code to run the experiments can be accessed from the following GitHub repository: https://github.com/Will-Doherty/CLOFAI.
format Preprint
id arxiv_https___arxiv_org_abs_2501_11140
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle CLOFAI: A Dataset of Real And Fake Image Classification Tasks for Continual Learning
Doherty, William
Lee, Anton
Gomes, Heitor Murilo
Computer Vision and Pattern Recognition
Artificial Intelligence
The rapid advancement of generative AI models capable of creating realistic media has led to a need for classifiers that can accurately distinguish between genuine and artificially-generated images. A significant challenge for these classifiers emerges when they encounter images from generative models that are not represented in their training data, usually resulting in diminished performance. A typical approach is to periodically update the classifier's training data with images from the new generative models then retrain the classifier on the updated dataset. However, in some real-life scenarios, storage, computational, or privacy constraints render this approach impractical. Additionally, models used in security applications may be required to rapidly adapt. In these circumstances, continual learning provides a promising alternative, as the classifier can be updated without retraining on the entire dataset. In this paper, we introduce a new dataset called CLOFAI (Continual Learning On Fake and Authentic Images), which takes the form of a domain-incremental image classification problem. Moreover, we showcase the applicability of this dataset as a benchmark for evaluating continual learning methodologies. In doing this, we set a baseline on our novel dataset using three foundational continual learning methods -- EWC, GEM, and Experience Replay -- and find that EWC performs poorly, while GEM and Experience Replay show promise, performing significantly better than a Naive baseline. The dataset and code to run the experiments can be accessed from the following GitHub repository: https://github.com/Will-Doherty/CLOFAI.
title CLOFAI: A Dataset of Real And Fake Image Classification Tasks for Continual Learning
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2501.11140