Generative Active Learning for Image Synthesis Personalization

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Zhang, Xulu, Zhang, Wengyu, Wei, Xiao-Yong, Wu, Jinlin, Zhang, Zhaoxiang, Lei, Zhen, Li, Qing
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866913316415209472
author Zhang, Xulu
Zhang, Wengyu
Wei, Xiao-Yong
Wu, Jinlin
Zhang, Zhaoxiang
Lei, Zhen
Li, Qing
author_facet Zhang, Xulu
Zhang, Wengyu
Wei, Xiao-Yong
Wu, Jinlin
Zhang, Zhaoxiang
Lei, Zhen
Li, Qing
contents This paper presents a pilot study that explores the application of active learning, traditionally studied in the context of discriminative models, to generative models. We specifically focus on image synthesis personalization tasks. The primary challenge in conducting active learning on generative models lies in the open-ended nature of querying, which differs from the closed form of querying in discriminative models that typically target a single concept. We introduce the concept of anchor directions to transform the querying process into a semi-open problem. We propose a direction-based uncertainty sampling strategy to enable generative active learning and tackle the exploitation-exploration dilemma. Extensive experiments are conducted to validate the effectiveness of our approach, demonstrating that an open-source model can achieve superior performance compared to closed-source models developed by large companies, such as Google's StyleDrop. The source code is available at https://github.com/zhangxulu1996/GAL4Personalization.
format Preprint
id arxiv_https___arxiv_org_abs_2403_14987
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Generative Active Learning for Image Synthesis Personalization
Zhang, Xulu
Zhang, Wengyu
Wei, Xiao-Yong
Wu, Jinlin
Zhang, Zhaoxiang
Lei, Zhen
Li, Qing
Computer Vision and Pattern Recognition
This paper presents a pilot study that explores the application of active learning, traditionally studied in the context of discriminative models, to generative models. We specifically focus on image synthesis personalization tasks. The primary challenge in conducting active learning on generative models lies in the open-ended nature of querying, which differs from the closed form of querying in discriminative models that typically target a single concept. We introduce the concept of anchor directions to transform the querying process into a semi-open problem. We propose a direction-based uncertainty sampling strategy to enable generative active learning and tackle the exploitation-exploration dilemma. Extensive experiments are conducted to validate the effectiveness of our approach, demonstrating that an open-source model can achieve superior performance compared to closed-source models developed by large companies, such as Google's StyleDrop. The source code is available at https://github.com/zhangxulu1996/GAL4Personalization.
title Generative Active Learning for Image Synthesis Personalization
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2403.14987