Ho-Youl Jung
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Ho-Youl Jung has a total of 5 co-authors. Here are the top co-authors by number of shared publications:
Gyu Sang Choi
Department of Information and Communication Engineering, Yeungnam University, Gyeongsan, 38541, Republic of Korea
1 shared publicationKook-Yeol Yoo
Department of Information and Communication Engineering, Yeungnam University, Gyeongsan, 38541, Republic of Korea
1 shared publicationMahammad Shareef Mekala
School of Computing, Robert Gordon University, Aberdeen, AB10 7QB, UK
1 shared publicationWoongkyu Park
Department of Information and Communication Engineering, Yeungnam University, Gyeongsan, 38541, Republic of Korea
1 shared publicationYeongyu Choi
RLRC for Autonomous Vehicle Parts and Materials Innovation, Yeungnam University, Gyeongsan, 38541, Republic of Korea
1 shared publication
Latest Publications
- Open Access
- 1 January 2025
- Published by Tech Science Press in Computers, Materials & Continua
- Vol. 82 (3) , 3965-3981
A Latency-Efficient Integration of Channel Attention for ConvNets
Designing fast and accurate neural networks is becoming essential in various vision tasks. Recently, the use of attention mechanisms has increased, aimed at enhancing the vision task performance by selectively focusing on relevant parts of the input. In this paper, we concentrate on squeeze-and-excitation (SE)-based channel attention, considering the trade-off between latency and accuracy. We propose a variation of the SE module, called squeeze-and-excitation with layer normalization (SELN), in which layer normalization (LN) replaces the sigmoid activation function. This approach reduces the vanishing gradient problem while enhancing feature diversity and discriminability of channel attention. In addition, we propose a latency-efficient model named SELNeXt, where the LN typically used in the ConvNext block is replaced by SELN to minimize additional latency-impacting operations. Through classification simulations on ImageNet-1k, we show that the top-1 accuracy of the proposed SELNeXt outperforms other ConvNeXt-based models in terms of latency efficiency. SELNeXt also achieves better object detection and instance segmentation performance on COCO than Swin Transformer and ConvNeXt for small-sized models. Our results indicate that LN could be a considerable candidate for replacing the activation function in attention mechanisms. In addition, SELNeXt achieves a better accuracy-latency trade-off, making it favorable for real-time applications and edge computing. The code is available at (accessed on 06 December 2024).
- 1 January 2025
- Published by Tech Science Press in Computers, Materials & Continua
- Vol. 82 (3) , 3965-3981
Open AccessA Latency-Efficient Integration of Channel Attention for ConvNets
Designing fast and accurate neural networks is becoming essential in various vision tasks. Recently, the use of attention mechanisms has increased, aimed at enhancing the vision task performance by selectively focusing on relevant parts of the input. In this paper, we concentrate on squeeze-and-excitation (SE)-based channel attention, considering the trade-off between latency and accuracy. We propose a variation of the SE module, called squeeze-and-excitation with layer normalization (SELN), in which layer normalization (LN) replaces the sigmoid activation function. This approach reduces the vanishing gradient problem while enhancing feature diversity and discriminability of channel attention. In addition, we propose a latency-efficient model named SELNeXt, where the LN typically used in the ConvNext block is replaced by SELN to minimize additional latency-impacting operations. Through classification simulations on ImageNet-1k, we show that the top-1 accuracy of the proposed SELNeXt outperforms other ConvNeXt-based models in terms of latency efficiency. SELNeXt also achieves better object detection and instance segmentation performance on COCO than Swin Transformer and ConvNeXt for small-sized models. Our results indicate that LN could be a considerable candidate for replacing the activation function in attention mechanisms. In addition, SELNeXt achieves a better accuracy-latency trade-off, making it favorable for real-time applications and edge computing. The code is available at (accessed on 06 December 2024).