Supplementary Material: Learning Semantic-aware Normalization for Generative Adversarial Networks

It can be observed that features with low resolutions (e.g., 8 8 64 64) Figure 2 shows the semantic interpolation results. Table 1: Comparison of baseline, random grouping and semantic grouping (i.e., the proposed SGM) Table 2: Conduct semantic-aware control at different on LSUN CATS [26] in terms of FID. Figure 1: Visualization of the semantics learned in different resolutions. We show 16 groups in each layer with the resolution increasing from 8 8 to 256 256. The attention maps are obtained by averaging the feature maps in a group. It can be observed that features with low resolutions (i.e., 8 8 64 64) show better performance in learning semantics (e.g., eyes, mouths and hair). We can realize independent control on fine-grained semantics by conducting interpolation in latent space.