TY  - CONF
AV  - none
ID  - scholars15447
TI  - Either crop or pad the input volume: What is beneficial for Convolutional Neural Network?
KW  - Convolution; Deep learning
KW  -  Convolutional kernel; Convolutional neural network; Cropping; Hyper-parameter; Kernel size; Number of layers; OR pads; Padding; Pooling; Window Size
KW  -  Convolutional neural networks
N2  - Convolutional Neural Network (CNN) is the most popular method of deep learning in the machine learning field. Training a CNN has always been a demanding task compared to other machine learning paradigms, and this is due to its big space of hyper-parameters such as convolutional kernel size, number of strides, number of layers, pooling window size, etc. What makes the CNN's huge hyper-parameters space optimization harder is that there is no universal robust theory supporting it, and any work flow proposed so far in literature is based on heuristics that are just rules of thumb and only depend on the dataset and problem at hand. In this work, it is empirically illustrated that the performance of a CNN is not linked only with the choice of the right hyper-parameters, but also linked to how some of the CNN operations are implemented. More specifically, the CNN performance is contrasted for two different implementations: cropping and padding the input volume. The results state that padding the input volume achieves higher accuracy and takes less time in training compared with cropping method. © 2021 IEEE.
N1  - cited By 1; Conference of 8th International Conference on Intelligent and Advanced Systems, ICIAS 2021 ; Conference Date: 13 July 2021 Through 15 July 2021; Conference Code:175661
PB  - Institute of Electrical and Electronics Engineers Inc.
SN  - 9781728176666
Y1  - 2021///
A1  - Al-Saggaf, U.M.
A1  - Botalb, A.
A1  - Moinuddin, M.
A1  - Alfakeh, S.A.
A1  - Ali, S.S.A.
A1  - Boon, T.T.
UR  - https://www.scopus.com/inward/record.uri?eid=2-s2.0-85124170608&doi=10.1109%2fICIAS49414.2021.9642661&partnerID=40&md5=fe97d0334bee476e8e7e0756fc5b0943
ER  -