Salvato in:
Dettagli Bibliografici
Autori principali: Zhou, Zikai, Zhang, Shuo, Wang, Ziruo, Chen, Huanran
Natura: Preprint
Pubblicazione: 2023
Soggetti:
Accesso online:https://arxiv.org/abs/2308.03321
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866913236781105152
author Zhou, Zikai
Zhang, Shuo
Wang, Ziruo
Chen, Huanran
author_facet Zhou, Zikai
Zhang, Shuo
Wang, Ziruo
Chen, Huanran
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2308_03321
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle AFN: Adaptive Fusion Normalization via an Encoder-Decoder Framework
Zhou, Zikai
Zhang, Shuo
Wang, Ziruo
Chen, Huanran
Machine Learning
Computer Vision and Pattern Recognition
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.
title AFN: Adaptive Fusion Normalization via an Encoder-Decoder Framework
topic Machine Learning
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2308.03321