论文标题
Pager：渐进属性引导可扩展的鲁棒图像生成
PAGER: Progressive Attribute-Guided Extendable Robust Image Generation
论文作者
论文摘要
这项工作提出了一种基于连续的子空间学习（SSL）的生成建模方法。与文献中的大多数生成模型不同，我们的方法不利用神经网络来分析基本源分布和合成图像。所得的方法称为渐进属性引导的可扩展鲁棒图像生成（PAGER）模型，在数学透明度，渐进式内容生成，较低的训练时间，较少的训练样本以及对条件图像生成的扩展性方面具有优势。 Pager由三个模块组成：核心生成器，分辨率增强器和质量助推器。核心发电机了解低分辨率图像的分布并执行无条件的图像生成。分辨率增强子通过条件产生增加图像分辨率。最后，质量助推器为生成的图像增添了细节。进行了有关MNIST，时尚 - 纳斯特和Celeba数据集的广泛实验，以证明Pager的生成性能。
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.
