On Leveraging Pretrained GANs for Generation with Limited Data
By Miaoyun Zhao, Yulai Cong, Lawrence Carin. 2020
102 citations recorded by the source corpus.
Subfields: Generative Models
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Generative Models
- Richard Zhang
- Eli Shechtman
- Jun-Yan Zhu
- Axel Sauer
- Andreas Geiger
- Jun Zhu
- Lawrence Carin
- Jianfeng Gao
Citations in the corpus
- Projected GANs Converge Faster (2021, background): “Work on leveraging pretrained representations for GANs can be divided into two categories: First, transferring parts of a GAN to a new dataset [15, 38, 65, 71] and, second, using pretrained models to control and improve GANs.”
- A Comprehensive Survey of Continual Learning: Theory, Method and Application (2023, methodology): “GAN-Memory [167] takes advantage of FiLM [201] and AdaFM [202] to learn task-specific parameters for each layer of a pre-trained generative model, while Authorized licensed use limited to the terms of the applicable license agreement with IEEE.”
- GAN Memory with No Forgetting (2020, methodology): “We demonstrate that mFiLM and mAdaFM can be leveraged to modulate the “style” of a source GAN model (including both the generator and discriminator) to form a generative/discriminative model capable of addressing a perceptually-distant target domain.”
- Ablating Concepts in Text-to-Image Diffusion Models (2023, background): “Fine-tuning aims to adapt the weights of a pretrained generative model to new domains [73, 46, 72, 41, 79, 34, 47, 80, 30, 35, 24, 44], downstream tasks [71, 54, 78], and test images [6, 53, 48, 31, 25, 49].”
- LFS-GAN: Lifelong Few-Shot Image Generation (2023, methodology): “It introduces variants of modulation algorithms, such as FiLM [37] and AdaFM [53], to learn the current task.”
- Lafite2: Few-shot Text-to-Image Generation (2022, background): “In the literature, it is known that training and fine-tuning large unconditional generative models with limited samples is not an easy task [13,22,42,43], not to mention that one needs to additionally consider image-text correspondence besides image quality.”
- Multi-Concept Customization of Text-to-Image Diffusion (2022, methodology): “A method of efficiently producing a whole distribution of images is leveraging a pretrained model and then using transfer learning [18,21,36,39,44,46–48,74, 75,82].”