TY - GEN
T1 - AstroNet
T2 - 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2023
AU - Han, Mengqiao
AU - Pan, Liyuan
AU - Liu, Xiabi
N1 - Publisher Copyright:
© 2023 IEEE.
PY - 2023
Y1 - 2023
N2 - Network structure learning aims to optimize network architectures and make them more efficient without compromising performance. In this paper, we first study the astrocytes, a new mechanism to regulate connections in the classic M-P neuron. Then, with the astrocytes, we propose an AstroNet that can adaptively optimize neuron connections and therefore achieves structure learning to achieve higher accuracy and efficiency. AstroNet is based on our built Astrocyte-Neuron model, with a temporal regulation mechanism and a global connection mechanism, which is inspired by the bidirectional communication property of astrocytes. With the model, the proposed AstroNet uses a neural network (NN) for performing tasks, and an astrocyte network (AN) to continuously optimize the connections of NN, i.e., assigning weight to the neuron units in the NN adaptively. Experiments on the classification task demonstrate that our AstroNet can efficiently optimize the network structure while achieving state-of-the-art (SOTA) accuracy.
AB - Network structure learning aims to optimize network architectures and make them more efficient without compromising performance. In this paper, we first study the astrocytes, a new mechanism to regulate connections in the classic M-P neuron. Then, with the astrocytes, we propose an AstroNet that can adaptively optimize neuron connections and therefore achieves structure learning to achieve higher accuracy and efficiency. AstroNet is based on our built Astrocyte-Neuron model, with a temporal regulation mechanism and a global connection mechanism, which is inspired by the bidirectional communication property of astrocytes. With the model, the proposed AstroNet uses a neural network (NN) for performing tasks, and an astrocyte network (AN) to continuously optimize the connections of NN, i.e., assigning weight to the neuron units in the NN adaptively. Experiments on the classification task demonstrate that our AstroNet can efficiently optimize the network structure while achieving state-of-the-art (SOTA) accuracy.
KW - Biometrics
UR - https://www.scopus.com/pages/publications/85175799719
U2 - 10.1109/CVPR52729.2023.01940
DO - 10.1109/CVPR52729.2023.01940
M3 - Conference contribution
AN - SCOPUS:85175799719
SN - 9798350301298
T3 - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
SP - 20258
EP - 20268
BT - Proceedings - 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2023
PB - IEEE Computer Society
Y2 - 18 June 2023 through 22 June 2023
ER -