arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 2510.26892cs.LGcs.AI
收藏

BI-DCGAN:一个理论上有根据的、用于高效和多样化GAN的贝叶斯框架

BI-DCGAN: A Theoretically Grounded Bayesian Framework for Efficient and Diverse GANs

Mahsa Valizadeh, Rui Tuo, James Caverlee

AI总结:

针对GAN模式崩溃问题,提出贝叶斯框架BI-DCGAN,通过集成Bayes by Backprop和平均场变分推断引入不确定性,并基于协方差矩阵分析首次证明其能增强样本多样性,实验证明该方法在保持高效的同时提升了输出的多样性与鲁棒性。

摘要:

生成对抗网络(GANs)擅长生成合成数据,但一直受到模式崩溃的困扰,即生成器产生狭窄范围的输出来欺骗判别器,却未能捕获完整的数据分布。这一局限性尤为棘手,因为生成模型正日益部署在同时要求多样性和不确定性感知的实际应用中。为此,我们提出了BI-DCGAN,它是DCGAN的贝叶斯扩展,在保持计算效率的同时将模型不确定性纳入生成过程。BI-DCGAN集成了Bayes by Backprop来学习网络权重的分布,并采用平均场变分推断在GAN训练期间高效逼近后验分布。我们基于协方差矩阵分析建立了首个理论证明,表明贝叶斯建模能增强GAN的样本多样性。我们通过在标准生成基准上的大量实验验证了这一理论结果,证明BI-DCGAN比传统DCGAN产生更多样和鲁棒的输出,同时保持了训练效率。这些发现使BI-DCGAN成为对多样性和不确定性均至关重要的应用的可扩展且适时的解决方案,而在这些应用中,扩散模型等现代替代方案仍过于消耗资源。

英文摘要:

Generative Adversarial Networks (GANs) are proficient at generating synthetic data but continue to suffer from mode collapse, where the generator produces a narrow range of outputs that fool the discriminator but fail to capture the full data distribution. This limitation is particularly problematic, as generative models are increasingly deployed in real-world applications that demand both diversity and uncertainty awareness. In response, we introduce BI-DCGAN, a Bayesian extension of DCGAN that incorporates model uncertainty into the generative process while maintaining computational efficiency. BI-DCGAN integrates Bayes by Backprop to learn a distribution over network weights and employs mean-field variational inference to efficiently approximate the posterior distribution during GAN training. We establishes the first theoretical proof, based on covariance matrix analysis, that Bayesian modeling enhances sample diversity in GANs. We validate this theoretical result through extensive experiments on standard generative benchmarks, demonstrating that BI-DCGAN produces more diverse and robust outputs than conventional DCGANs, while maintaining training efficiency. These findings position BI-DCGAN as a scalable and timely solution for applications where both diversity and uncertainty are critical, and where modern alternatives like diffusion models remain too resource-intensive.

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。

↑