PAGER: Progressive Attribute-Guided Extendable Robust Image Generation
This work addresses image generation for domains requiring mathematical transparency and efficiency, but it is incremental as it builds on existing subspace learning techniques.
The paper tackles image generation by proposing PAGER, a non-neural network method based on successive subspace learning, which achieves robust performance with fewer training samples and lower training time, as demonstrated on MNIST, Fashion-MNIST, and CelebA datasets.
This work presents a generative modeling approach based on successive subspace learning (SSL). Unlike most generative models in the literature, our method does not utilize neural networks to analyze the underlying source distribution and synthesize images. The resulting method, called the progressive attribute-guided extendable robust image generative (PAGER) model, has advantages in mathematical transparency, progressive content generation, lower training time, robust performance with fewer training samples, and extendibility to conditional image generation. PAGER consists of three modules: core generator, resolution enhancer, and quality booster. The core generator learns the distribution of low-resolution images and performs unconditional image generation. The resolution enhancer increases image resolution via conditional generation. Finally, the quality booster adds finer details to generated images. Extensive experiments on MNIST, Fashion-MNIST, and CelebA datasets are conducted to demonstrate generative performance of PAGER.