TY - GEN
T1 - FuzzyDCNN
T2 - 2021 IEEE CIS International Conference on Fuzzy Systems, FUZZ 2021
AU - Lin, Qiao
AU - Chen, Xin
AU - Chen, Chao
AU - Garibaldi, Jonathan M.
N1 - Publisher Copyright:
© 2021 IEEE.
PY - 2021/7/11
Y1 - 2021/7/11
N2 - Convolutional neural networks (CNNs) have achieved the state-of-the-art performance in many application areas, due to the capability of automatically extracting and aggregating spatial and channel-wise features from images. Most recent studies have concentrated on modifying convolutional kernel size to achieve multi-scale spatial information. In this paper, we introduce a novel fuzzy integral module to the CNNs for fusing the information across feature channels. The fuzzy integral is a mathematical aggregation operator and is widely used in decision level fusion. Herein, we utilize a special case of fuzzy integrals namely ordered weight averaging (OWA) to merge information at feature level. Three publicly available datasets were used to evaluate the proposed fuzzy CNN model for image segmentation. The results show that the proposed fuzzy module helps in reducing the baseline model parameters by 58.54% while producing higher segmentation accuracy (measured by Dice) than the baseline method and a similar method reported in the literature.
AB - Convolutional neural networks (CNNs) have achieved the state-of-the-art performance in many application areas, due to the capability of automatically extracting and aggregating spatial and channel-wise features from images. Most recent studies have concentrated on modifying convolutional kernel size to achieve multi-scale spatial information. In this paper, we introduce a novel fuzzy integral module to the CNNs for fusing the information across feature channels. The fuzzy integral is a mathematical aggregation operator and is widely used in decision level fusion. Herein, we utilize a special case of fuzzy integrals namely ordered weight averaging (OWA) to merge information at feature level. Three publicly available datasets were used to evaluate the proposed fuzzy CNN model for image segmentation. The results show that the proposed fuzzy module helps in reducing the baseline model parameters by 58.54% while producing higher segmentation accuracy (measured by Dice) than the baseline method and a similar method reported in the literature.
UR - http://www.scopus.com/inward/record.url?scp=85114690649&partnerID=8YFLogxK
U2 - 10.1109/FUZZ45933.2021.9494456
DO - 10.1109/FUZZ45933.2021.9494456
M3 - Conference contribution
T3 - IEEE International Conference on Fuzzy Systems
SP - 1
EP - 7
BT - IEEE CIS International Conference on Fuzzy Systems 2021, FUZZ 2021 - Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 11 July 2021 through 14 July 2021
ER -