Max Pooling
Max Pooling is a downsampling technique in convolutional neural networks that belongs to the class of aggregation features and is distinguished by selecting the maximum value within localized regions of a feature map to reduce spatial dimensionality while preserving dominant activation patterns.
666
Publications
85.6K
Citations
2.4K
Authors
790
Institutions
Publications per year
2017–2026
504
Variants
Max-pooling
Parents
666
Learning Deep Features for Discriminative Localization
Bolei Zhou, Aditya Khosla, Àgata Lapedriza et al. · 2016 · 10.8K citations · Full text
Striving for Simplicity: The All Convolutional Net
Jost Tobias Springenberg, Alexey Dosovitskiy, Thomas Brox et al. · arXiv (Cornell University) · 2014 · 2.6K citations · Full text
1–5 of 666
2.4K
Dalle Molle Institute for Artificial Intelligence Research, Switzerland
7 publications · 2.1K citations
7
h-index
Dalle Molle Institute for Artificial Intelligence Research, Switzerland
6 publications · 2K citations
6
h-index
6
h-index
6
h-index
6
h-index
1–5 of 2.4K
790

Chinese Academy of Sciences
Beijing, China
19 h-index
73 publications
19.6K citations
University of Chinese Academy of Sciences
Beijing, China
10 h-index
25 publications
1.9K citations
Institute of Automation
Beijing, China
10 h-index
27 publications
2.7K citations
Tsinghua University
Beijing, China
10 h-index
20 publications
966 citations

Sun Yat-sen University
Guangzhou, China
10 h-index
30 publications
982 citations

Peking University
Beijing, China
10 h-index
29 publications
1.2K citations

University of Leicester
Leicester, United Kingdom
9 h-index
12 publications
1K citations
University of Illinois Urbana-Champaign
Urbana, United States
9 h-index
20 publications
9.7K citations
1–8 of 790
Repository · 72 publications · 12.8K citations
38
h-index
34 publications · 2K citations
23
h-index
15 publications · 1.4K citations
13
h-index
10 publications · 611 citations
10
h-index
9 publications · 381 citations
9
h-index
1–5