Where is my spot? Few-shot image generation via latent subspace optimization
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...
Saved in:
Main Authors: | , , , , |
---|---|
Format: | text |
Language: | English |
Published: |
Institutional Knowledge at Singapore Management University
2023
|
Subjects: | |
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 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Singapore Management University |
Language: | English |
id |
sg-smu-ink.sis_research-9450 |
---|---|
record_format |
dspace |
spelling |
sg-smu-ink.sis_research-94502024-01-04T09:53:31Z Where is my spot? Few-shot image generation via latent subspace optimization ZHENG, Chenxi LIU, Bangzhen ZHANG, Huaidong XU, Xuemiao HE, Shengfeng 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. 2023-06-01T07:00:00Z text application/pdf https://ink.library.smu.edu.sg/sis_research/8447 info:doi/10.1109/CVPR52729.2023.00319 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 http://creativecommons.org/licenses/by-nc-nd/4.0/ Research Collection School Of Computing and Information Systems eng Institutional Knowledge at Singapore Management University Computer vision Codes Image synthesis Training data Robustness Pattern recognition Optimization Artificial Intelligence and Robotics |
institution |
Singapore Management University |
building |
SMU Libraries |
continent |
Asia |
country |
Singapore Singapore |
content_provider |
SMU Libraries |
collection |
InK@SMU |
language |
English |
topic |
Computer vision Codes Image synthesis Training data Robustness Pattern recognition Optimization Artificial Intelligence and Robotics |
spellingShingle |
Computer vision Codes Image synthesis Training data Robustness Pattern recognition Optimization Artificial Intelligence and Robotics ZHENG, Chenxi LIU, Bangzhen ZHANG, Huaidong XU, Xuemiao HE, Shengfeng Where is my spot? Few-shot image generation via latent subspace optimization |
description |
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. |
format |
text |
author |
ZHENG, Chenxi LIU, Bangzhen ZHANG, Huaidong XU, Xuemiao HE, Shengfeng |
author_facet |
ZHENG, Chenxi LIU, Bangzhen ZHANG, Huaidong XU, Xuemiao HE, Shengfeng |
author_sort |
ZHENG, Chenxi |
title |
Where is my spot? Few-shot image generation via latent subspace optimization |
title_short |
Where is my spot? Few-shot image generation via latent subspace optimization |
title_full |
Where is my spot? Few-shot image generation via latent subspace optimization |
title_fullStr |
Where is my spot? Few-shot image generation via latent subspace optimization |
title_full_unstemmed |
Where is my spot? Few-shot image generation via latent subspace optimization |
title_sort |
where is my spot? few-shot image generation via latent subspace optimization |
publisher |
Institutional Knowledge at Singapore Management University |
publishDate |
2023 |
url |
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 |
_version_ |
1787590751082774528 |