TY - GEN
T1 - UTILIZING EXCESS RESOURCES IN TRAINING NEURAL NETWORKS
AU - Henig, Amit
AU - Giryes, Raja
N1 - Publisher Copyright:
© 2022 IEEE.
PY - 2022
Y1 - 2022
N2 - In this work, we suggest Kernel Filtering Linear Overparameterization (KFLO), where a linear cascade of filtering layers is used during training to improve network performance in test time. We implement this cascade in a kernel filtering fashion, which prevents the trained architecture from becoming unnecessarily deeper. This also allows using our approach with almost any network architecture and let combining the filtering layers into a single layer in test time. Thus, our approach does not add computational complexity during inference. We demonstrate the advantage of KFLO on various network models and datasets in supervised learning.
AB - In this work, we suggest Kernel Filtering Linear Overparameterization (KFLO), where a linear cascade of filtering layers is used during training to improve network performance in test time. We implement this cascade in a kernel filtering fashion, which prevents the trained architecture from becoming unnecessarily deeper. This also allows using our approach with almost any network architecture and let combining the filtering layers into a single layer in test time. Thus, our approach does not add computational complexity during inference. We demonstrate the advantage of KFLO on various network models and datasets in supervised learning.
KW - kernel filtering/composition
KW - linear overparameterization
KW - structural reparameterization
UR - http://www.scopus.com/inward/record.url?scp=85146694202&partnerID=8YFLogxK
U2 - 10.1109/ICIP46576.2022.9897994
DO - 10.1109/ICIP46576.2022.9897994
M3 - ???researchoutput.researchoutputtypes.contributiontobookanthology.conference???
AN - SCOPUS:85146694202
T3 - Proceedings - International Conference on Image Processing, ICIP
SP - 1941
EP - 1945
BT - 2022 IEEE International Conference on Image Processing, ICIP 2022 - Proceedings
PB - IEEE Computer Society
T2 - 29th IEEE International Conference on Image Processing, ICIP 2022
Y2 - 16 October 2022 through 19 October 2022
ER -