Bum Jun Kim

According to our database, Bum Jun Kim authored at least 18 papers between 2019 and 2024.

Collaborative distances:

• Dijkstra number of six.
• Erdős number of five.

2024

Steel product number recognition framework using semantic mask-conditioned diffusion model with limited data.

Hyeyeon Choi, Jong Pil Yun, Bum Jun Kim, Hyeonah Jang, WooSang Shin, Sang Woo Kim

J. Ind. Inf. Integr., March, 2024

On the ideal number of groups for isometric gradient propagation.

Bum Jun Kim, Hyeyeon Choi, Hyeonah Jang, Sang Woo Kim

Neurocomputing, March, 2024

Scale Equalization for Multi-Level Feature Fusion.

Bum Jun Kim, Sang Woo Kim

CoRR, 2024

2023

Improved robustness of vision transformers via prelayernorm in patch embedding.

Bum Jun Kim, Hyeyeon Choi, Hyeonah Jang, Dong Gu Lee, Wonseok Jeong, Sang Woo Kim

Pattern Recognit., September, 2023

Extending class activation mapping using Gaussian receptive field.

Bum Jun Kim, Gyogwon Koo, Hyeyeon Choi, Sang Woo Kim

Comput. Vis. Image Underst., June, 2023

Smooth momentum: improving lipschitzness in gradient descent.

Bum Jun Kim, Hyeyeon Choi, Hyeonah Jang, Sang Woo Kim

Appl. Intell., June, 2023

Dead pixel test using effective receptive field.

Bum Jun Kim, Hyeyeon Choi, Hyeonah Jang, Dong Gu Lee, Wonseok Jeong, Sang Woo Kim

Pattern Recognit. Lett., March, 2023

Analysis of NaN Divergence in Training Monocular Depth Estimation Model.

Bum Jun Kim, Hyeonah Jang, Sang Woo Kim

CoRR, 2023

Resolution-Aware Design of Atrous Rates for Semantic Segmentation Networks.

Bum Jun Kim, Hyeyeon Choi, Hyeonah Jang, Sang Woo Kim

CoRR, 2023

Two-Stage Billet Identification Number Recognition Using Label Distribution.

Hyeonah Jang, Hyeyeon Choi, Bum Jun Kim, Sang Woo Kim, Gyogwon Koo

IEEE Access, 2023

How to use dropout correctly on residual networks with batch normalization.

Bum Jun Kim, Hyeyeon Choi, Hyeonah Jang, Donggeon Lee, Sang Woo Kim

Proceedings of the Uncertainty in Artificial Intelligence, 2023

Understanding Gaussian Attention Bias of Vision Transformers Using Effective Receptive Fields.

Bum Jun Kim, Hyeyeon Choi, Hyeonah Jang, Sang Woo Kim

Proceedings of the 34th British Machine Vision Conference 2023, 2023

2022

Attention-Based Multimodal Image Feature Fusion Module for Transmission Line Detection.

Hyeyeon Choi, Jong Pil Yun, Bum Jun Kim, Hyeonah Jang, Sang Woo Kim

IEEE Trans. Ind. Informatics, 2022

Multi-Level Stacked Regression for predicting electricity consumption of Hot Rolling Mill.

Yeon Tak Kim, Bum Jun Kim, Sang Woo Kim

Expert Syst. Appl., 2022

Guidelines for the Regularization of Gammas in Batch Normalization for Deep Residual Networks.

Bum Jun Kim, Hyeyeon Choi, Hyeonah Jang, Dong Gu Lee, Wonseok Jeong, Sang Woo Kim

CoRR, 2022

2021

Weakly supervised power line detection algorithm using a recursive noisy label update with refined broken line segments.

Hyeyeon Choi, Gyogwon Koo, Bum Jun Kim, Sang Woo Kim

Expert Syst. Appl., 2021

Improved Robustness of Vision Transformer via PreLayerNorm in Patch Embedding.

Bum Jun Kim, Hyeyeon Choi, Hyeonah Jang, Dong Gu Lee, Wonseok Jeong, Sang Woo Kim

CoRR, 2021

2019

Real-time Power Line Detection Network using Visible Light and Infrared Images.

Hyeyeon Choi, Gyogwon Koo, Bum Jun Kim, Sang Woo Kim

Proceedings of the 2019 International Conference on Image and Vision Computing New Zealand, 2019