2 papers
cs.CV2024
Towards Lifelong Few-Shot Customization of Text-to-Image Diffusion
Nan Song, Xiaofeng Yang, Ze Yang +1
Lifelong few-shot customization for text-to-image diffusion aims to continually generalize existing models for new tasks with minimal data while preserving old knowledge. Current c…
cs.CV2024
3D-VirtFusion: Synthetic 3D Data Augmentation through Generative Diffusion Models and Controllable Editing
Shichao Dong, Ze Yang, Guosheng Lin
Data augmentation plays a crucial role in deep learning, enhancing the generalization and robustness of learning-based models. Standard approaches involve simple transformations li…