Learning to Optimize Domain Specific Normalization for Domain Generalization
| Autor: | Dongwan Kim, Bohyung Han, Yumin Suh, Jong-Woo Han, Geeho Kim, Seonguk Seo |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
Normalization (statistics)
Domain adaptation business.industry Computer science 05 social sciences Pattern recognition 010501 environmental sciences 01 natural sciences 0502 economics and business Deep neural networks Generalizability theory Affine transformation Artificial intelligence 050207 economics business 0105 earth and related environmental sciences |
| Zdroj: | Computer Vision – ECCV 2020 ISBN: 9783030585419 ECCV (22) |
| Popis: | We propose a simple but effective multi-source domain generalization technique based on deep neural networks by incorporating 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. The normalization statistics are kept track of separately for each normalization type if necessary. Specifically, we employ batch and instance normalizations in our implementation to identify the best combination of these two normalization methods in each domain. The optimized normalization layers are effective to enhance the generalizability of the learned model. We demonstrate the state-of-the-art accuracy of our algorithm in the standard domain generalization benchmarks, as well as viability to further tasks such as multi-source domain adaptation and domain generalization in the presence of label noise. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|