Scalable Fine-grained Generated Image Classification Based on Deep Metric Learning
This addresses the need for forensic tools to keep up with rapidly emerging new types of generated images, though it is incremental as it builds on existing deep metric learning approaches.
The authors tackled the problem of classifying multiple types of high-quality generated images that are difficult to distinguish from real ones, proposing a scalable deep metric learning framework that achieves better detection performance on new types through fine-tuning.
Recently, generated images could reach very high quality, even human eyes could not tell them apart from real images. Although there are already some methods for detecting generated images in current forensic community, most of these methods are used to detect a single type of generated images. The new types of generated images are emerging one after another, and the existing detection methods cannot cope well. These problems prompted us to propose a scalable framework for multi-class classification based on deep metric learning, which aims to classify the generated images finer. In addition, we have increased the scalability of our framework to cope with the constant emergence of new types of generated images, and through fine-tuning to make the model obtain better detection performance on the new type of generated data.