Where is my spot? Few-shot image generation via latent subspace optimization

• Main Authors: ZHENG, Chenxi, LIU, Bangzhen, ZHANG, Huaidong, XU, Xuemiao, HE, Shengfeng
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2023
• Subjects: Computer vision; Codes; Image synthesis; Training data; Robustness; Pattern recognition; Optimization; Artificial Intelligence and Robotics
• Online Access: https://ink.library.smu.edu.sg/sis_research/8447; https://ink.library.smu.edu.sg/context/sis_research/article/9450/viewcontent/Zheng_Where_Is_My_Spot_Few_Shot_Image_Generation_via_Latent_Subspace_CVPR_2023_paper.pdf
• Institution: Singapore Management University

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.