Synthetic Image
Synthetic image generation leverages machine learning models, such as Generative Adversarial Networks (GANs) and Diffusion Models, to create realistic artificial images for various applications. Current research focuses on improving the realism and diversity of synthetic images, developing methods for detecting synthetic images and attributing them to their source models, and exploring their use in data augmentation to address data scarcity issues in diverse fields like medical imaging, material science, and autonomous driving. The ability to generate high-quality synthetic images has significant implications for training machine learning models, particularly in domains where real data is limited, expensive, or ethically challenging to obtain, while also raising concerns about the potential for misuse in creating deepfakes and other forms of misinformation.
Papers
Is Synthetic Image Useful for Transfer Learning? An Investigation into Data Generation, Volume, and Utilization
Yuhang Li, Xin Dong, Chen Chen, Jingtao Li, Yuxin Wen, Michael Spranger, Lingjuan Lyu
Enhance Image Classification via Inter-Class Image Mixup with Diffusion Model
Zhicai Wang, Longhui Wei, Tan Wang, Heyu Chen, Yanbin Hao, Xiang Wang, Xiangnan He, Qi Tian
Synthetic Medical Imaging Generation with Generative Adversarial Networks For Plain Radiographs
John R. McNulty, Lee Kho, Alexandria L. Case, Charlie Fornaca, Drew Johnston, David Slater, Joshua M. Abzug, Sybil A. Russell