TY - GEN
T1 - Spiking GLOM
T2 - 30th IEEE International Conference on Image Processing, ICIP 2023
AU - Kang, Peng
AU - Banerjee, Srutarshi
AU - Chopp, Henry
AU - Katsaggelos, Aggelos
AU - Cossairt, Oliver Strides
N1 - Publisher Copyright:
© 2023 IEEE.
PY - 2023
Y1 - 2023
N2 - Today, artificial neural networks (ANNs) have demonstrated extraordinary abilities in many cognition tasks. Nevertheless, the limitations of many ANN-based techniques are evident, such as the low energy efficiency and the lack of interpretability. To alleviate these problems, researchers have directed their attention to bio-inspired models, including energy-efficient Spiking Neural Networks (SNNs) and the GLOM model representing part-whole hierarchies in neural networks. In this paper, we propose a novel bio-inspired solution to next-generation object recognition. Specifically, we propose an energy-efficient and interpretable model - Spiking GLOM by introducing spiking neurons and neuronal dynamics into the GLOM model. Moreover, we evaluate our model and its variants on CIFAR-10. Extensive experiments demonstrate the effectiveness of our proposed models for object recognition and show the superiority of our models in energy efficiency and interpretability.
AB - Today, artificial neural networks (ANNs) have demonstrated extraordinary abilities in many cognition tasks. Nevertheless, the limitations of many ANN-based techniques are evident, such as the low energy efficiency and the lack of interpretability. To alleviate these problems, researchers have directed their attention to bio-inspired models, including energy-efficient Spiking Neural Networks (SNNs) and the GLOM model representing part-whole hierarchies in neural networks. In this paper, we propose a novel bio-inspired solution to next-generation object recognition. Specifically, we propose an energy-efficient and interpretable model - Spiking GLOM by introducing spiking neurons and neuronal dynamics into the GLOM model. Moreover, we evaluate our model and its variants on CIFAR-10. Extensive experiments demonstrate the effectiveness of our proposed models for object recognition and show the superiority of our models in energy efficiency and interpretability.
KW - energy efficiency
KW - interpretability
KW - object recognition
KW - Spiking GLOM
KW - Spiking Neural Networks
UR - http://www.scopus.com/inward/record.url?scp=85180761608&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85180761608&partnerID=8YFLogxK
U2 - 10.1109/ICIP49359.2023.10222367
DO - 10.1109/ICIP49359.2023.10222367
M3 - Conference contribution
AN - SCOPUS:85180761608
T3 - Proceedings - International Conference on Image Processing, ICIP
SP - 950
EP - 954
BT - 2023 IEEE International Conference on Image Processing, ICIP 2023 - Proceedings
PB - IEEE Computer Society
Y2 - 8 October 2023 through 11 October 2023
ER -