IGAN：一种基于 inception 的新模型，用于使用生成对抗网络进行稳定且高保真的图像合成
IGAN: A New Inception-based Model for Stable and High-Fidelity Image Synthesis Using Generative Adversarial Networks
AI总结：
IGAN通过引入更深的inception启发式卷积和扩张卷积，提升图像生成质量与训练稳定性，实现更优的FID和IS指标。
摘要：
生成对抗网络（GANs）面临在高质量图像生成和训练稳定性之间取得最佳平衡的重大挑战。最近的技术，如DCGAN、BigGAN和StyleGAN，提高了视觉保真度；然而，这些技术在高网络深度时通常难以克服模式崩溃和梯度不稳定的难题。本文提出了一种新的GAN结构模型，该模型结合了更深的inception启发式卷积和扩张卷积。这种新型模型被称为Inception生成对抗网络（IGAN）。IGAN模型通过减少模式崩溃以及防止消失和爆炸梯度，从而在生成高质量合成图像的同时保持训练稳定性。我们提出的IGAN模型在CUB-200和ImageNet数据集上分别实现了Fréchet Inception距离（FID）为13.12和15.08，相较于最先进的GANs，FID提高了28-33%。此外，IGAN模型获得了Inception分数（IS）为9.27和68.25，反映了改进的图像多样性和生成质量。最后，dropout和频谱归一化两种技术被用于生成器和判别器结构中，以进一步缓解梯度爆炸和过拟合问题。这些发现证实了IGAN模型在训练稳定性与图像生成质量之间取得平衡的潜力，构成了一种可扩展且计算高效的高保真图像合成框架。
英文摘要：
Generative Adversarial Networks (GANs) face a significant challenge of striking an optimal balance between high-quality image generation and training stability. Recent techniques, such as DCGAN, BigGAN, and StyleGAN, improve visual fidelity; however, such techniques usually struggle with mode collapse and unstable gradients at high network depth. This paper proposes a novel GAN structural model that incorporates deeper inception-inspired convolution and dilated convolution. This novel model is termed the Inception Generative Adversarial Network (IGAN). The IGAN model generates high-quality synthetic images while maintaining training stability, by reducing mode collapse as well as preventing vanishing and exploding gradients. Our proposed IGAN model achieves the Frechet Inception Distance (FID) of 13.12 and 15.08 on the CUB-200 and ImageNet datasets, respectively, representing a 28-33% improvement in FID over the state-of-the-art GANs. Additionally, the IGAN model attains an Inception Score (IS) of 9.27 and 68.25, reflecting improved image diversity and generation quality. Finally, the two techniques of dropout and spectral normalization are utilized in both the generator and discriminator structures to further mitigate gradient explosion and overfitting. These findings confirm that the IGAN model potentially balances training stability with image generation quality, constituting a scalable and computationally efficient framework for high-fidelity image synthesis.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
