NP-DRAW: A Non-Parametric Structured Latent Variable Model for Image Generation

Abstract

In this paper, we present a non-parametric structured latent variable model for image generation, called NP-DRAW, which sequentially draws on a latent canvas in a part-by-part fashion and then decodes the image from the canvas. Our key contributions are as follows. 1) We propose a non-parametric prior distribution over the appearance of image parts so that the latent variable ``what-to-draw'' per step becomes a categorical random variable. This improves the expressiveness and greatly eases the learning compared to Gaussians used in the literature. 2) We model the sequential dependency structure of parts via a Transformer, which is more powerful and easier to train compared to RNNs used in the literature. 3) We propose an effective heuristic parsing algorithm to pre-train the prior. Experiments on MNIST, Omniglot, CIFAR-10, and CelebA show that our method significantly outperforms previous structured image models like DRAW and AIR and is competitive to other generic generative models. Moreover, we show that our model's inherent compositionality and interpretability bring significant benefits in the low-data learning regime and latent space editing. Code is available at https://github.com/ZENGXH/NPDRAW.

arXiv commentUAI2021, code at https://github.com/ZENGXH/NPDRAW

References in corpus (21)

• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
• Denoising Diffusion Probabilistic Models
• GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
• Spectral Normalization for Generative Adversarial Networks
• Categorical Reparameterization with Gumbel-Softmax
• Neural Discrete Representation Learning
• Improved Training of Wasserstein GANs
• Variational Inference with Normalizing Flows
• Generative Modeling by Estimating Gradients of the Data Distribution
• DRAW: A Recurrent Neural Network For Image Generation
• Density estimation using Real NVP
• Generative Moment Matching Networks
• NVAE: A Deep Hierarchical Variational Autoencoder
• Attend, Infer, Repeat: Fast Scene Understanding with Generative Models
• Generating Diverse High-Fidelity Images with VQ-VAE-2
• Implicit Generation and Generalization in Energy-Based Models
• One-Shot Generalization in Deep Generative Models
• CoSE: Compositional Stroke Embeddings
• Exemplar VAE: Linking Generative Models, Nearest Neighbor Retrieval, and Data Augmentation
• VQ-DRAW: A Sequential Discrete VAE