TY - GEN
T1 - Fully Automatic CNN Design with Inception Blocks
AU - Barakbayeva, Togzhan
AU - Demirci, M. Fatih
N1 - Publisher Copyright:
© 2021 SPIE
PY - 2021
Y1 - 2021
N2 - Convolutional Neural Networks (CNNs) are widely used in image classification tasks and have demonstrated promising classification accuracy results. Designing a CNN architecture requires a manual adjustment of parameters through a series of experiments as well as sufficient knowledge both in the problem domain and CNN architecture design. Therefore, it is extremely difficult for users without prior experience to design a promising CNN for their purposes. To solve this issue, various solutions on the automatic construction of CNN architectures are proposed, including but not limited to a genetic algorithm AE-CNN1 for automatically evolving CNN design using ResNet and DenseNet blocks. In this paper, a significant improvement of the afore-mentioned solution by the addition of Inception blocks is introduced. Performance of the algorithm is assessed on the CINIC-10 benchmark dataset without and with the usage of Inception blocks. As it can be observed from the outcome of the experiment, the addition of Inception blocks positively affects the final classification accuracy. The proposed algorithm does not only improve the current solution but also keeps the advantages of automatic CNN without requesting any manual interventions.
AB - Convolutional Neural Networks (CNNs) are widely used in image classification tasks and have demonstrated promising classification accuracy results. Designing a CNN architecture requires a manual adjustment of parameters through a series of experiments as well as sufficient knowledge both in the problem domain and CNN architecture design. Therefore, it is extremely difficult for users without prior experience to design a promising CNN for their purposes. To solve this issue, various solutions on the automatic construction of CNN architectures are proposed, including but not limited to a genetic algorithm AE-CNN1 for automatically evolving CNN design using ResNet and DenseNet blocks. In this paper, a significant improvement of the afore-mentioned solution by the addition of Inception blocks is introduced. Performance of the algorithm is assessed on the CINIC-10 benchmark dataset without and with the usage of Inception blocks. As it can be observed from the outcome of the experiment, the addition of Inception blocks positively affects the final classification accuracy. The proposed algorithm does not only improve the current solution but also keeps the advantages of automatic CNN without requesting any manual interventions.
KW - Automatic CNN construction
KW - Convolutional neural networks
KW - Genetic algorithms
UR - http://www.scopus.com/inward/record.url?scp=85109417791&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85109417791&partnerID=8YFLogxK
U2 - 10.1117/12.2601117
DO - 10.1117/12.2601117
M3 - Conference contribution
AN - SCOPUS:85109417791
T3 - Proceedings of SPIE - The International Society for Optical Engineering
BT - Thirteenth International Conference on Digital Image Processing, ICDIP 2021
A2 - Jiang, Xudong
A2 - Fujita, Hiroshi
PB - SPIE
T2 - 13th International Conference on Digital Image Processing, ICDIP 2021
Y2 - 20 May 2021 through 23 May 2021
ER -