Spatial Dependency Networks: Neural Layers for Improved Generative Image Modeling
arXiv:2103.08877
Abstract
How to improve generative modeling by better exploiting spatial regularities and coherence in images? We introduce a novel neural network for building image generators (decoders) and apply it to variational autoencoders (VAEs). In our spatial dependency networks (SDNs), feature maps at each level of a deep neural net are computed in a spatially coherent way, using a sequential gating-based mechanism that distributes contextual information across 2-D space. We show that augmenting the decoder of a hierarchical VAE by spatial dependency layers considerably improves density estimation over baseline convolutional architectures and the state-of-the-art among the models within the same class. Furthermore, we demonstrate that SDN can be applied to large images by synthesizing samples of high quality and coherence. In a vanilla VAE setting, we find that a powerful SDN decoder also improves learning disentangled representations, indicating that neural architectures play an important role in this task. Our results suggest favoring spatial dependency over convolutional layers in various VAE settings. The accompanying source code is given at https://github.com/djordjemila/sdn.
References in corpus (14)
- PyTorch: An Imperative Style, High-Performance Deep Learning Library
- Auto-Encoding Variational Bayes
- A Simple Framework for Contrastive Learning of Visual Representations
- Self-Attention Generative Adversarial Networks
- Stochastic Backpropagation and Approximate Inference in Deep Generative Models
- Conditional Image Generation with PixelCNN Decoders
- Pixel Recurrent Neural Networks
- Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representations
- NVAE: A Deep Hierarchical Variational Autoencoder
- Variational Lossy Autoencoder
- ReNet: A Recurrent Neural Network Based Alternative to Convolutional Networks
- Generative Image Modeling Using Spatial LSTMs
- Generating High Fidelity Images with Subscale Pixel Networks and Multidimensional Upscaling
- Augmented Normalizing Flows: Bridging the Gap Between Generative Flows and Latent Variable Models