Attentive Normalization for Conditional Image Generation
This work addresses the challenge of synthesizing detailed images for categories with complicated structures, representing an incremental improvement over existing methods like self-attention GAN.
The paper tackles the problem of generating images with complex structures by introducing attentive normalization to model long-range dependencies, achieving improved performance in class-conditional image generation and semantic inpainting tasks.
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.