FewGAN: Generating from the Joint Distribution of a Few Images
Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review
Documents
- FewGAN
Submitted manuscript, 1.8 MB, PDF document
We introduce FewGAN, a generative model for generating novel, high-quality and diverse images whose patch distribution lies in the joint patch distribution of a small number of N > 1 training samples. The method is, in essence, a hierarchical patch-GAN that applies quantization at the first coarse scale, in a similar fashion to VQ-GAN, followed by a pyramid of residual fully convolutional GANs at finer scales. Our key idea is to first use quantization to learn a fixed set of patch embeddings for training images. We then use a separate set of side images to model the structure of generated images using an autoregressive model trained on the learned patch embeddings of training images. Using quantization at the coarsest scale allows the model to generate both conditional and unconditional novel images. Subsequently, a patch-GAN renders the fine details, resulting in high-quality images. In an extensive set of experiments, it is shown that FewGAN outperforms baselines both quantitatively and qualitatively.
Original language | English |
---|---|
Title of host publication | 2022 IEEE International Conference on Image Processing, ICIP 2022 - Proceedings |
Number of pages | 5 |
Publisher | IEEE |
Publication date | 2022 |
Pages | 751-755 |
ISBN (Electronic) | 9781665496209 |
DOIs | |
Publication status | Published - 2022 |
Event | 29th IEEE International Conference on Image Processing, ICIP 2022 - Bordeaux, France Duration: 16 Oct 2022 → 19 Oct 2022 |
Conference
Conference | 29th IEEE International Conference on Image Processing, ICIP 2022 |
---|---|
Land | France |
By | Bordeaux |
Periode | 16/10/2022 → 19/10/2022 |
Sponsor | The Institute of Electrical and Electronics Engineers Signal Processing Society |
Series | Proceedings - International Conference on Image Processing, ICIP |
---|---|
ISSN | 1522-4880 |
Bibliographical note
Publisher Copyright:
© 2022 IEEE.
- Few-Shot learning, GANs, Quantization
Research areas
ID: 344653001