TY - GEN
T1 - Efficient Training of EfficientNetV2-S Using AdaBelief Optimizer
AU - Jeon, Hyung Joon
AU - Jeon, Jae Wook
N1 - Publisher Copyright:
© 2022 IEEE.
PY - 2022
Y1 - 2022
N2 - The EfficientNetV2 architectures have classification accuracies exceeding 80% on the Imagenet-1K/21K datasets. Here, the networks used to be trained using stochastic gradient descent with momentum ($SGD+M$) as the optimizer. Such a method is known to be effective but takes too much time, making it impractical to train the networks from scratch especially when computational power is limited. To address this, we provide a guide on how to use the AdaBelief Optimizer for training EfficientNetV2-S. Results show that, even without complex training configurations, using AdaBelief can lead the EfficientNetV2-S network to achieve a top-1 accuracy as high as 80% on the Imagenet-1K validation set within 80 epochs of training.
AB - The EfficientNetV2 architectures have classification accuracies exceeding 80% on the Imagenet-1K/21K datasets. Here, the networks used to be trained using stochastic gradient descent with momentum ($SGD+M$) as the optimizer. Such a method is known to be effective but takes too much time, making it impractical to train the networks from scratch especially when computational power is limited. To address this, we provide a guide on how to use the AdaBelief Optimizer for training EfficientNetV2-S. Results show that, even without complex training configurations, using AdaBelief can lead the EfficientNetV2-S network to achieve a top-1 accuracy as high as 80% on the Imagenet-1K validation set within 80 epochs of training.
KW - AdaBelief
KW - deep learning
KW - EfficientNetV2-S
KW - image classification
UR - https://www.scopus.com/pages/publications/85143794571
U2 - 10.1109/ICCE-Asia57006.2022.9954726
DO - 10.1109/ICCE-Asia57006.2022.9954726
M3 - Conference contribution
AN - SCOPUS:85143794571
T3 - 2022 IEEE International Conference on Consumer Electronics-Asia, ICCE-Asia 2022
BT - 2022 IEEE International Conference on Consumer Electronics-Asia, ICCE-Asia 2022
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2022 IEEE International Conference on Consumer Electronics-Asia, ICCE-Asia 2022
Y2 - 26 October 2022 through 28 October 2022
ER -