Name
Abstract | ||
|---|---|---|
Traditional normalization techniques (e.g., Batch Normalization and Instance Normalization) generally and simplistically assume that training and test data follow the same distribution. As distribution shifts are inevitable in real-world applications, well-trained models with previous normalization methods can perform badly in new environments. Can we develop new normalization methods to improve g... |
Year | DOI | Venue |
|---|---|---|
2021 | 10.1109/ICCV48922.2021.00012 | 2021 IEEE/CVF International Conference on Computer Vision (ICCV) |
Keywords | DocType | ISBN |
Training,Bridges,Computer vision,Codes,Robustness,Task analysis | Conference | 978-1-6654-2812-5 |
Citations | PageRank | References |
0 | 0.34 | 0 |
Authors | ||
6 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Zhiqiang Tang | 1 | 0 | 0.34 |
| Yunhe Gao | 2 | 0 | 0.68 |
| Yi Zhu | 3 | 0 | 0.34 |
| Zhi Zhang | 4 | 0 | 0.34 |
| Mu Li | 5 | 913 | 42.35 |
| Dimitris N. Metaxas | 6 | 8834 | 952.25 |