Kyoung-Hak Lee
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Kyoung-Hak Lee has a total of 5 co-authors. Here are the top co-authors by number of shared publications:
- Hyung-Hwa Ko
Department of Electronics and Communication Engineering, Kwangwoon University, Seoul 01897, Korea
1 shared publication - June-Kyoung Lee
NAONWORKS
1 shared publication - Min-Soo Kang
Department of Bigdata Medical Convergence, Eulji University, Seongnam 13135, Republic of Korea
1 shared publication Seong-Woo Lee
NAONWORKS
1 shared publication- Yeonghun Lee
Department of Electronics and Communication Engineering, Kwangwoon University, Seoul 01897, Korea
1 shared publication
Latest Publications
- Open Access
- 13 September 2022
- Published by MDPI AG in Applied Sciences
- Vol. 12 (18) , 9160
A Study on the Channel Expansion VAE for Content-Based Image Retrieval
Content-based image retrieval (CBIR) focuses on video searching with fine-tuning of pre-trained off-the-shelf features. CBIR is an intuitive method for image retrieval, although it still requires labeled datasets for fine-tuning due to the inefficiency caused by annotation. Therefore, we explored an unsupervised model for feature extraction of image contents. We used a variational auto-encoder (VAE) expanding channel of neural networks and studied the activation of layer outputs. In this study, the channel expansion method boosted the capability of image retrieval by exploring more kernels and selecting a layer of comparatively activated object region. The experiment included a comparison of channel expansion and visualization of each layer in the encoder network. The proposed model achieved (52.7%) mAP, which outperformed (36.5%) the existing VAE on the MNIST dataset.
- 13 September 2022
- Published by MDPI AG in Applied Sciences
- Vol. 12 (18) , 9160
Open AccessA Study on the Channel Expansion VAE for Content-Based Image Retrieval
Content-based image retrieval (CBIR) focuses on video searching with fine-tuning of pre-trained off-the-shelf features. CBIR is an intuitive method for image retrieval, although it still requires labeled datasets for fine-tuning due to the inefficiency caused by annotation. Therefore, we explored an unsupervised model for feature extraction of image contents. We used a variational auto-encoder (VAE) expanding channel of neural networks and studied the activation of layer outputs. In this study, the channel expansion method boosted the capability of image retrieval by exploring more kernels and selecting a layer of comparatively activated object region. The experiment included a comparison of channel expansion and visualization of each layer in the encoder network. The proposed model achieved (52.7%) mAP, which outperformed (36.5%) the existing VAE on the MNIST dataset.
- 19 September 2018
- Published by Springer Nature in Wireless Personal Communications
- Vol. 105 (2) , 545-565
An Implementation of Convergence Security Solution for Overcoming of Security Vulnerabilities in Industrial Control Communication Network
- 19 September 2018
- Published by Springer Nature in Wireless Personal Communications
- Vol. 105 (2) , 545-565
An Implementation of Convergence Security Solution for Overcoming of Security Vulnerabilities in Industrial Control Communication Network