.png){kind=icon}
返回
DuDGAN: Improving Class-Conditional GANs via Dual-Diffusion
.png){kind=icon}
OA
AI
DOI：10.1109/ACCESS.2024.3372996.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Class-conditional image generation using generative adversarial networks (GANs) has been investigated through various techniques; however, it continues to face challenges such as mode collapse, training instability, and low-quality output in cases of datasets with high intra-class variation. Furthermore, most GANs often converge in larger iterations, resulting in poor iteration efficacy in training procedures. While Diffusion-GAN has shown potential in generating realistic samples, it has a critical limitation in generating class-conditional samples. To overcome these limitations, we propose a novel approach for class-conditional image generation using GANs called DuDGAN, which incorporates a dual diffusion-based noise injection process. DuDGAN consists of three unique networks: a discriminator, a generator, and a classifier. During the training process, Gaussian-mixture noises are injected into the two noise-aware networks, the discriminator and the classifier, in distinct ways. This noisy data helps to prevent overfitting by gradually introducing more challenging tasks, leading to improved model performance. As a result, DuDGAN outperforms state-of-the-art conditional GAN models for image generation in terms of performance. We evaluated DuDGAN using the AFHQ, Food-101, CIFAR-10, and BAAT datasets and observed superior results across metrics such as FID, KID, Precision, and Recall score compared with comparison models; FID decreases 12.9% and 5.1% on average for AFHQ and CIFAR-10, respectively, highlighting the effectiveness of the proposed approach.
Keyword:
Training
Image synthesis
Generative adversarial networks
Mathematical models
Generators
Computational modeling
Probabilistic logic
Deep learning
Conditional image generation
deep learning
diffusion-based probabilistic models
generative adversarial networks
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Effects of feeding rates on growth, body composition and nutrient metabolism in striped bass (Morone saxatilis) fingerlings.png)
Aquaculture
AquacultureIF0
PREAI
分享收藏The Effect of 40-Hz Light Therapy on Amyloid Load in Patients with Prodromal and Clinical Alzheimer’s Disease40Hz光疗法对前驱和临床阿尔茨海默病患者淀粉样蛋白负荷的影响
OAAI
OAAI分享收藏A new Jurassic theropod from China documents a transitional step in the macrostructure of feathers
PREAI
分享收藏
查看更多内容