Zobrazeno 1 - 10
of 190
pro vyhledávání: '"Liao, Shengcai"'
Despite promising progress in face swapping task, realistic swapped images remain elusive, often marred by artifacts, particularly in scenarios involving high pose variation, color differences, and occlusion. To address these issues, we propose a nov
Externí odkaz:
http://arxiv.org/abs/2409.07269
Autor:
Fang, Guian, Yan, Wenbiao, Guo, Yuanfan, Han, Jianhua, Jiang, Zutao, Xu, Hang, Liao, Shengcai, Liang, Xiaodan
Text-to-image diffusion models have significantly advanced in conditional image generation. However, these models usually struggle with accurately rendering images featuring humans, resulting in distorted limbs and other anomalies. This issue primari
Externí odkaz:
http://arxiv.org/abs/2407.06937
Autor:
Huang, Jiehui, Dong, Xiao, Song, Wenhui, Li, Hanhui, Zhou, Jun, Cheng, Yuhao, Liao, Shutao, Chen, Long, Yan, Yiqiang, Liao, Shengcai, Liang, Xiaodan
Diffusion-based technologies have made significant strides, particularly in personalized and customized facialgeneration. However, existing methods face challenges in achieving high-fidelity and detailed identity (ID)consistency, primarily due to ins
Externí odkaz:
http://arxiv.org/abs/2404.16771
Image-language models with prompt learning have shown remarkable advances in numerous downstream vision tasks. Nevertheless, conventional prompt learning methods overfit their training distribution and lose the generalization ability on test distribu
Externí odkaz:
http://arxiv.org/abs/2402.10099
Prototype-based meta-learning has emerged as a powerful technique for addressing few-shot learning challenges. However, estimating a deterministic prototype using a simple average function from a limited number of examples remains a fragile process.
Externí odkaz:
http://arxiv.org/abs/2306.14770
Facial expression editing has attracted increasing attention with the advance of deep neural networks in recent years. However, most existing methods suffer from compromised editing fidelity and limited usability as they either ignore pose variations
Externí odkaz:
http://arxiv.org/abs/2304.08938
Publikováno v:
CVPR2023
Generative Adversarial Networks (GANs) rely heavily on large-scale training data for training high-quality image generation models. With limited training data, the GAN discriminator often suffers from severe overfitting which directly leads to degrad
Externí odkaz:
http://arxiv.org/abs/2303.17158
Domain adaptation tackles the challenge of generalizing knowledge acquired from a source domain to a target domain with different data distributions. Traditional domain adaptation methods presume that the classes in the source and target domains are
Externí odkaz:
http://arxiv.org/abs/2303.05933
In this paper, we propose energy-based sample adaptation at test time for domain generalization. Where previous works adapt their models to target domains, we adapt the unseen target samples to source-trained models. To this end, we design a discrimi
Externí odkaz:
http://arxiv.org/abs/2302.11215
Most existing few-shot learning (FSL) methods require a large amount of labeled data in meta-training, which is a major limit. To reduce the requirement of labels, a semi-supervised meta-training (SSMT) setting has been proposed for FSL, which includ
Externí odkaz:
http://arxiv.org/abs/2207.06817