The success of deep learning is inseparable from normalization layers. Researchers have proposed various normalization functions, and each of them has both advantages and disadvantages. In response, efforts have been made to design a unified normalization function that combines all normalization procedures and mitigates their weaknesses. We also proposed a new normalization function called Adaptive Fusion Normalization. Through experiments, we demonstrate AFN outperforms the previous normalization techniques in domain generalization and image classification tasks.
@article{arxiv.2308.03321,
title = {AFN: Adaptive Fusion Normalization via an Encoder-Decoder Framework},
author = {Zikai Zhou and Shuo Zhang and Ziruo Wang and Huanran Chen},
journal= {arXiv preprint arXiv:2308.03321},
year = {2024}
}
Comments
arXiv admin note: text overlap with arXiv:2106.01899 by other authors