.png){kind=icon}
返回
Locally Conditioned GANs: Self-Supervised Local Patch Representation Learning for Conditional Generation
.png){kind=icon}
OA
AI
DOI：10.1109/ACCESS.2024.3418884.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Existing conditional generation models using generative adversarial networks (GANs) suffer from two common limitations: 1) they heavily rely on supervision, or 2) their performance is favorable to the scenario of creating only small changes. This study aims to address both issues by introducing new locally conditioned generative adversarial networks (LCGAN). Inspired by self-supervised representation learning, we devise intuitive learning signals and training tactics to learn the local patch encoding for developing the locally controllable latent space of GANs. Powered by local patch encoding with our novel loss design, the proposed model successfully performs locally conditioned image generation while covering various attributes. Utilizing LCGAN, ordinary users can easily design an image by browsing its patch-level appearance from various patch examples, even including out-of-domain examples. Besides, LCGAN, with latent optimization, offers high-quality results in local editing. Experimental evaluations verify that our model is effective in both conditional generation and local editing in achieving both image quality and fidelity. Our method is the most preferred by 55.78% of user study participants, and it achieved Fr & eacute;chet inception distance scores of 16.24 and 15.01 on the FFHQ and AFHQ-cat datasets, respectively. Especially, a comprehensive user study supports that: 1) trade-off between quality and fidelity exists in existing methods and 2) our model is the first to alleviate their trade-off relationships, showing the potential in practical image editing applications.
Keyword:
Training
Image synthesis
Generative adversarial networks
Semantics
Vectors
Representation learning
Image reconstruction
Condition monitoring
Generative adversarial network
conditional generation
image composition
期刊
IF:
3.6
论文数:
9.8W
被引数:
29.4W
机构
引用论文
分享收藏Sensorless Control of Z Source Inverter fed BLDC Motor Drive by FOC - DTC Hybrid Control Strategy Using Fuzzy Logic Controller采用模糊逻辑控制器的foc-dtc混合控制策略的Z源逆变器馈电BLDC电机驱动的无传感器控制
PREAI
分享收藏Varicella-zoster virus inhibits autophagosome-lysosome fusion and the degradation stage of mTOR-mediated autophagic flux.png)
Virology
VirologyIF0
PREAI
分享收藏Scene Text Segmentation via Multi-Task Cascade Transformer With Paired Data SynthesisIEEE ACCESSOAAI
IEEE ACCESSIF3.6
OAAI分享收藏分享收藏
查看更多内容