Learning to Optimize Domain-Specific Normalization for Domain Generalization
ECCV 2020 | We propose a simple but effective multi-source domain-generalization technique based on deep neural networks that incorporates optimized normalization layers that are specific to individual domains. Our approach employs multiple normalization methods while learning separate affine parameters per domain. For each domain, the activations are normalized by a weighted average of multiple normalization statistics. If necessary, these normalization statistics are tracked separately for each normalization type.
Collaborators: Seonguk Seo, Yumin Suh, Dongwan Kim, Geeho Kim, Jongwoo Han, Bohyung Han