@online{Fan2211.04393,
TITLE = {Normalization Perturbation: A Simple Domain Generalization Method for Real-World Domain Shifts},
AUTHOR = {Fan, Qi and Segu, Mattia and Tai, Yu-Wing and Yu, Fisher and Tang, Chi-Keung and Schiele, Bernt and Dai, Dengxin},
LANGUAGE = {eng},
URL = {https://arxiv.org/abs/2211.04393},
EPRINT = {2211.04393},
EPRINTTYPE = {arXiv},
YEAR = {2022},
ABSTRACT = {Improving model's generalizability against domain shifts is crucial,<br>especially for safety-critical applications such as autonomous driving.<br>Real-world domain styles can vary substantially due to environment changes and<br>sensor noises, but deep models only know the training domain style. Such domain<br>style gap impedes model generalization on diverse real-world domains. Our<br>proposed Normalization Perturbation (NP) can effectively overcome this domain<br>style overfitting problem. We observe that this problem is mainly caused by the<br>biased distribution of low-level features learned in shallow CNN layers. Thus,<br>we propose to perturb the channel statistics of source domain features to<br>synthesize various latent styles, so that the trained deep model can perceive<br>diverse potential domains and generalizes well even without observations of<br>target domain data in training. We further explore the style-sensitive channels<br>for effective style synthesis. Normalization Perturbation only relies on a<br>single source domain and is surprisingly effective and extremely easy to<br>implement. Extensive experiments verify the effectiveness of our method for<br>generalizing models under real-world domain shifts.<br>},
}