EUNNet: Efficient UN-Normalized Convolution Layer for Stable Training of Deep Residual Networks Without Batch Normalization Layer

journal contribution

posted on 2025-03-18, 02:49 authored by Khanh-Binh Nguyen, Jaehyuk Choi, Joon-Sung Yang

EUNNet: Efficient UN-Normalized Convolution Layer for Stable Training of Deep Residual Networks Without Batch Normalization Layer

History

Journal

IEEE Access

Volume

11

Pagination

76977-76988

Location

Piscataway, N.J.

Open access

Yes

ISSN

2169-3536

eISSN

2169-3536

Language

eng

Publication classification

C1.1 Refereed article in a scholarly journal

Publisher

Institute of Electrical and Electronics Engineers

Publication URL

https://doi.org/10.1109/access.2023.3244072

Usage metrics

Categories

Keywords

batch normalization Computer Science Computer Science, Information Systems computer vision Deep neural networks Engineering Engineering, Electrical & Electronic image classification object detection overfitting Science & Technology Technology Telecommunications

Licence

CC BY-NC-ND 4.0

Exports