|
|
|
|
LEADER |
01000naa a22002652 4500 |
001 |
NLM355232901 |
003 |
DE-627 |
005 |
20231226063921.0 |
007 |
cr uuu---uuuuu |
008 |
231226s2023 xx |||||o 00| ||eng c |
024 |
7 |
|
|a 10.1109/TPAMI.2023.3235369
|2 doi
|
028 |
5 |
2 |
|a pubmed24n1184.xml
|
035 |
|
|
|a (DE-627)NLM355232901
|
035 |
|
|
|a (NLM)37018583
|
040 |
|
|
|a DE-627
|b ger
|c DE-627
|e rakwb
|
041 |
|
|
|a eng
|
100 |
1 |
|
|a Xu, Yuhui
|e verfasserin
|4 aut
|
245 |
1 |
0 |
|a BNET
|b Batch Normalization With Enhanced Linear Transformation
|
264 |
|
1 |
|c 2023
|
336 |
|
|
|a Text
|b txt
|2 rdacontent
|
337 |
|
|
|a ƒaComputermedien
|b c
|2 rdamedia
|
338 |
|
|
|a ƒa Online-Ressource
|b cr
|2 rdacarrier
|
500 |
|
|
|a Date Completed 06.06.2023
|
500 |
|
|
|a Date Revised 06.06.2023
|
500 |
|
|
|a published: Print-Electronic
|
500 |
|
|
|a Citation Status PubMed-not-MEDLINE
|
520 |
|
|
|a Batch normalization (BN) is a fundamental unit in modern deep neural networks. However, BN and its variants focus on normalization statistics but neglect the recovery step that uses linear transformation to improve the capacity of fitting complex data distributions. In this paper, we demonstrate that the recovery step can be improved by aggregating the neighborhood of each neuron rather than just considering a single neuron. Specifically, we propose a simple yet effective method named batch normalization with enhanced linear transformation (BNET) to embed spatial contextual information and improve representation ability. BNET can be easily implemented using the depth-wise convolution and seamlessly transplanted into existing architectures with BN. To our best knowledge, BNET is the first attempt to enhance the recovery step for BN. Furthermore, BN is interpreted as a special case of BNET from both spatial and spectral views. Experimental results demonstrate that BNET achieves consistent performance gains based on various backbones in a wide range of visual tasks. Moreover, BNET can accelerate the convergence of network training and enhance spatial information by assigning important neurons with large weights accordingly
|
650 |
|
4 |
|a Journal Article
|
700 |
1 |
|
|a Xie, Lingxi
|e verfasserin
|4 aut
|
700 |
1 |
|
|a Xie, Cihang
|e verfasserin
|4 aut
|
700 |
1 |
|
|a Dai, Wenrui
|e verfasserin
|4 aut
|
700 |
1 |
|
|a Mei, Jieru
|e verfasserin
|4 aut
|
700 |
1 |
|
|a Qiao, Siyuan
|e verfasserin
|4 aut
|
700 |
1 |
|
|a Shen, Wei
|e verfasserin
|4 aut
|
700 |
1 |
|
|a Xiong, Hongkai
|e verfasserin
|4 aut
|
700 |
1 |
|
|a Yuille, Alan
|e verfasserin
|4 aut
|
773 |
0 |
8 |
|i Enthalten in
|t IEEE transactions on pattern analysis and machine intelligence
|d 1979
|g 45(2023), 7 vom: 09. Juli, Seite 9225-9232
|w (DE-627)NLM098212257
|x 1939-3539
|7 nnns
|
773 |
1 |
8 |
|g volume:45
|g year:2023
|g number:7
|g day:09
|g month:07
|g pages:9225-9232
|
856 |
4 |
0 |
|u http://dx.doi.org/10.1109/TPAMI.2023.3235369
|3 Volltext
|
912 |
|
|
|a GBV_USEFLAG_A
|
912 |
|
|
|a SYSFLAG_A
|
912 |
|
|
|a GBV_NLM
|
912 |
|
|
|a GBV_ILN_350
|
951 |
|
|
|a AR
|
952 |
|
|
|d 45
|j 2023
|e 7
|b 09
|c 07
|h 9225-9232
|