Scalable Fine-grained Generated Image Classification Based on Deep Metric Learning
arXiv:1912.11082
Abstract
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.
References in corpus (9)
- Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
- Progressive Growing of GANs for Improved Quality, Stability, and Variation
- BEGAN: Boundary Equilibrium Generative Adversarial Networks
- Identification of Deep Network Generated Images Using Disparities in Color Components
- ForensicTransfer: Weakly-supervised Domain Adaptation for Forgery Detection
- IntroVAE: Introspective Variational Autoencoders for Photographic Image Synthesis
- Detecting GAN-generated Imagery using Color Cues
- Universal Image Manipulation Detection using Deep Siamese Convolutional Neural Network
- Noiseprint: a CNN-based camera model fingerprint