CLOFAI: A Dataset of Real And Fake Image Classification Tasks for Continual Learning
Authors:
Preprint
Abstract
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.Keywords
All Related Versions
This publication has 7 references indexed in Scilit:
- Diffusion Noise Feature: Accurate and Fast Generated Image Detection2025
- Level Up the Deepfake Detection: A Method to Effectively Discriminate Images Generated by GAN Architectures and Diffusion Models2024
- CIFAKE: Image Classification and Explainable Identification of AI-Generated Synthetic ImagesIEEE Access, 2024
- An improvised CNN model for fake image detectionInternational Journal of Information Technology, 2022
- Investigating the impact of data normalization on classification performanceApplied Soft Computing, 2020
- Overcoming catastrophic forgetting in neural networksProceedings of the National Academy of Sciences, 2017
- Using Noise to Compute Error Surfaces in Connectionist Networks: A Novel Means of Reducing Catastrophic ForgettingNeural Computation, 2002