Attentive Normalization for Conditional Image Generation

Abstract

Traditional convolution-based generative adversarial networks synthesize images based on hierarchical local operations, where long-range dependency relation is implicitly modeled with a Markov chain. It is still not sufficient for categories with complicated structures. In this paper, we characterize long-range dependence with attentive normalization (AN), which is an extension to traditional instance normalization. Specifically, the input feature map is softly divided into several regions based on its internal semantic similarity, which are respectively normalized. It enhances consistency between distant regions with semantic correspondence. Compared with self-attention GAN, our attentive normalization does not need to measure the correlation of all locations, and thus can be directly applied to large-size feature maps without much computational burden. Extensive experiments on class-conditional image generation and semantic inpainting verify the efficacy of our proposed module.

CVPR 2020

References in corpus (18)

• Adam: A Method for Stochastic Optimization
• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
• GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
• Large Scale GAN Training for High Fidelity Natural Image Synthesis
• Spectral Normalization for Generative Adversarial Networks
• Instance Normalization: The Missing Ingredient for Fast Stylization
• Self-Attention Generative Adversarial Networks
• Conditional Image Synthesis With Auxiliary Classifier GANs
• Progressive Growing of GANs for Improved Quality, Stability, and Variation
• Data Augmentation Generative Adversarial Networks
• The relativistic discriminator: a key element missing from standard GAN
• cGANs with Projection Discriminator
• Generative Image Inpainting with Contextual Attention
• High-Fidelity Image Generation With Fewer Labels
• Interlaced Sparse Self-Attention for Semantic Segmentation
• Neural Expectation Maximization
• Consistency Regularization for Generative Adversarial Networks