Publication Type
Conference Proceeding Article
Version
publishedVersion
Publication Date
6-2023
Abstract
Image generation relies on massive training data that can hardly produce diverse images of an unseen category according to a few examples. In this paper, we address this dilemma by projecting sparse few-shot samples into a continuous latent space that can potentially generate infinite unseen samples. The rationale behind is that we aim to locate a centroid latent position in a conditional StyleGAN, where the corresponding output image on that centroid can maximize the similarity with the given samples. Although the given samples are unseen for the conditional StyleGAN, we assume the neighboring latent subspace around the centroid belongs to the novel category, and therefore introduce two latent subspace optimization objectives. In the first one we use few-shot samples as positive anchors of the novel class, and adjust the StyleGAN to produce the corresponding results with the new class label condition. The second objective is to govern the generation process from the other way around, by altering the centroid and its surrounding latent subspace for a more precise generation of the novel class. These reciprocal optimization objectives inject a novel class into the StyleGAN latent subspace, and therefore new unseen samples can be easily produced by sampling images from it. Extensive experiments demonstrate superior few-shot generation performances compared with state-of-the-art methods, especially in terms of diversity and generation quality. Code is available at https://github.com/chansey0529/LSO.
Keywords
Computer vision, Codes, Image synthesis, Training data, Robustness, Pattern recognition, Optimization
Discipline
Artificial Intelligence and Robotics
Research Areas
Software and Cyber-Physical Systems
Publication
Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), Vancouver, BC, Canada, June 17-24, 2023
First Page
3272
Last Page
3281
ISBN
9798350301304
Identifier
10.1109/CVPR52729.2023.00319
Publisher
IEEE Computer Society
City or Country
New York, NY, USA
Citation
ZHENG, Chenxi; LIU, Bangzhen; ZHANG, Huaidong; XU, Xuemiao; and HE, Shengfeng.
Where is my spot? Few-shot image generation via latent subspace optimization. (2023). Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), Vancouver, BC, Canada, June 17-24, 2023. 3272-3281.
Available at: https://ink.library.smu.edu.sg/sis_research/8447
Copyright Owner and License
Authors
Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-No Derivative Works 4.0 International License.
Additional URL
https://doi.org/10.1109/CVPR52729.2023.00319