Deep Generative Modeling with Backward Stochastic Differential Equations
This work addresses the challenge of uncertainty modeling in generative AI for domains like computer vision, though it appears incremental by integrating existing techniques.
The paper tackles the problem of generating high-dimensional complex data, such as images, by proposing BSDE-Gen, a deep generative model that combines backward stochastic differential equations with neural networks, achieving competitive results in image generation tasks.
This paper proposes a novel deep generative model, called BSDE-Gen, which combines the flexibility of backward stochastic differential equations (BSDEs) with the power of deep neural networks for generating high-dimensional complex target data, particularly in the field of image generation. The incorporation of stochasticity and uncertainty in the generative modeling process makes BSDE-Gen an effective and natural approach for generating high-dimensional data. The paper provides a theoretical framework for BSDE-Gen, describes its model architecture, presents the maximum mean discrepancy (MMD) loss function used for training, and reports experimental results.