Bum Jun Kim - RankMe

41 papers A* 1A 2Misc 1Journal 37

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	Approximation rates in Besov norms and sample-complexity of Kolmogorov-Arnold networks with residual connections. Neural Networks Anastasis Kratsios, Bum Jun Kim, Takashi Furuya
2026	J	`jnl`	Discovering Scaling Exponents with Physics-Informed Müntz-Szász Networks. CoRR Gnankan Landry Regis N'guessan, Bum Jun Kim
2026	J	`jnl`	Noise-robust anomaly detection framework using temporal features for industrial applications. Comput. Electr. Eng. Hyeonah Jang, Taehan Lee, Bum Jun Kim, Hyeyeon Choi, Sang Woo Kim
2026	J	`jnl`	Radial Müntz-Szász Networks: Neural Architectures with Learnable Power Bases for Multidimensional Singularities. CoRR Gnankan Landry Regis N'guessan, Bum Jun Kim
2026	J	`jnl`	Residual Koopman Spectral Profiling for Predicting and Preventing Transformer Training Instability. CoRR Bum Jun Kim, Shohei Taniguchi, Makoto Kawano, Yusuke Iwasawa, Yutaka Matsuo
2026	J	`jnl`	Resolution-aware design of atrous rates for semantic segmentation networks. Eng. Appl. Artif. Intell. Bum Jun Kim, Hyeyeon Choi, Hyeonah Jang, Sang Woo Kim
2026	J	`jnl`	Stochastic subsampling with average pooling. Appl. Soft Comput. Bum Jun Kim, Sang Woo Kim
2025	J	`jnl`	Analysis of NaN divergence in training monocular depth estimation model. Appl. Soft Comput. Bum Jun Kim, Hyeonah Jang, Sang Woo Kim
2025	A*	`conf`	Configuring Data Augmentations to Reduce Variance Shift in Positional Embedding of Vision Transformers. AAAI Bum Jun Kim, Sang Woo Kim
2025	J	`jnl`	Disappearance of Timestep Embedding: A Case Study on Neural ODE and Diffusion Models. Trans. Mach. Learn. Res. Bum Jun Kim, Yoshinobu Kawahara, Sang Woo Kim
2025	J	`jnl`	Font conversion for steel product number recognition: A conditioned diffusion model approach. Adv. Eng. Informatics Taehan Lee, Hyeyeon Choi, Bum Jun Kim, Hyeonah Jang, Donggeon Lee, Sang Woo Kim
2025	J	`jnl`	Temperature-Free Loss Function for Contrastive Learning. CoRR Bum Jun Kim, Sang Woo Kim
2025	J	`jnl`	Unlocking Noise-Resistant Vision: Key Architectural Secrets for Robust Models. CoRR Bum Jun Kim, Makoto Kawano, Yusuke Iwasawa, Yutaka Matsuo
2024	J	`jnl`	Configuring Data Augmentations to Reduce Variance Shift in Positional Embedding of Vision Transformers. CoRR Bum Jun Kim, Sang Woo Kim
2024	J	`jnl`	Guidelines for the Regularization of Gammas in Batch Normalization for Deep Residual Networks. ACM Trans. Intell. Syst. Technol. Bum Jun Kim, Hyeyeon Choi, Hyeonah Jang, Sang Woo Kim
2024	J	`jnl`	On the ideal number of groups for isometric gradient propagation. Neurocomputing Bum Jun Kim, Hyeyeon Choi, Hyeonah Jang, Sang Woo Kim
2024	J	`jnl`	Scale Equalization for Multi-Level Feature Fusion. CoRR Bum Jun Kim, Sang Woo Kim
2024	J	`jnl`	Scale Equalization for Multi-Level Feature Fusion. Trans. Mach. Learn. Res. Bum Jun Kim, Sang Woo Kim
2024	J	`jnl`	Steel product number recognition framework using semantic mask-conditioned diffusion model with limited data. J. Ind. Inf. Integr. Hyeyeon Choi, Jong Pil Yun, Bum Jun Kim, Hyeonah Jang, Woosang Shin, Sang Woo Kim
2024	J	`jnl`	Stochastic Subsampling With Average Pooling. CoRR Bum Jun Kim, Sang Woo Kim
2024	J	`jnl`	The Disappearance of Timestep Embedding in Modern Time-Dependent Neural Networks. CoRR Bum Jun Kim, Yoshinobu Kawahara, Sang Woo Kim
2023	J	`jnl`	Analysis of NaN Divergence in Training Monocular Depth Estimation Model. CoRR Bum Jun Kim, Hyeonah Jang, Sang Woo Kim
2023	J	`jnl`	Dead pixel test using effective receptive field. Pattern Recognit. Lett. Bum Jun Kim, Hyeyeon Choi, Hyeonah Jang, Dong Gu Lee, Wonseok Jeong, Sang Woo Kim
2023	J	`jnl`	Extending class activation mapping using Gaussian receptive field. Comput. Vis. Image Underst. Bum Jun Kim, Gyogwon Koo, Hyeyeon Choi, Sang Woo Kim
2023	J	`jnl`	How to Use Dropout Correctly on Residual Networks with Batch Normalization. CoRR Bum Jun Kim, Hyeyeon Choi, Hyeonah Jang, Donggeon Lee, Sang Woo Kim
2023	A	`conf`	How to use dropout correctly on residual networks with batch normalization. UAI Bum Jun Kim, Hyeyeon Choi, Hyeonah Jang, Donggeon Lee, Sang Woo Kim
2023	J	`jnl`	Improved robustness of vision transformers via prelayernorm in patch embedding. Pattern Recognit. Bum Jun Kim, Hyeyeon Choi, Hyeonah Jang, Dong Gu Lee, Wonseok Jeong, Sang Woo Kim
2023	J	`jnl`	On the Ideal Number of Groups for Isometric Gradient Propagation. CoRR Bum Jun Kim, Hyeyeon Choi, Hyeonah Jang, Sang Woo Kim
2023	J	`jnl`	Resolution-Aware Design of Atrous Rates for Semantic Segmentation Networks. CoRR Bum Jun Kim, Hyeyeon Choi, Hyeonah Jang, Sang Woo Kim
2023	J	`jnl`	Smooth momentum: improving lipschitzness in gradient descent. Appl. Intell. Bum Jun Kim, Hyeyeon Choi, Hyeonah Jang, Sang Woo Kim
2023	J	`jnl`	Two-Stage Billet Identification Number Recognition Using Label Distribution. IEEE Access Hyeonah Jang, Hyeyeon Choi, Bum Jun Kim, Sang Woo Kim, Gyogwon Koo
2023	A	`conf`	Understanding Gaussian Attention Bias of Vision Transformers Using Effective Receptive Fields. BMVC Bum Jun Kim, Hyeyeon Choi, Hyeonah Jang, Sang Woo Kim
2023	J	`jnl`	Understanding Gaussian Attention Bias of Vision Transformers Using Effective Receptive Fields. CoRR Bum Jun Kim, Hyeyeon Choi, Hyeonah Jang, Sang Woo Kim
2022	J	`jnl`	Attention-Based Multimodal Image Feature Fusion Module for Transmission Line Detection. IEEE Trans. Ind. Informatics Hyeyeon Choi, Jong Pil Yun, Bum Jun Kim, Hyeonah Jang, Sang Woo Kim
2022	J	`jnl`	Guidelines for the Regularization of Gammas in Batch Normalization for Deep Residual Networks. CoRR Bum Jun Kim, Hyeyeon Choi, Hyeonah Jang, Dong Gu Lee, Wonseok Jeong, Sang Woo Kim
2022	J	`jnl`	Multi-Level Stacked Regression for predicting electricity consumption of Hot Rolling Mill. Expert Syst. Appl. Yeon Tak Kim, Bum Jun Kim, Sang Woo Kim
2021	J	`jnl`	Dead Pixel Test Using Effective Receptive Field. CoRR Bum Jun Kim, Hyeyeon Choi, Hyeonah Jang, Dong Gu Lee, Wonseok Jeong, Sang Woo Kim
2021	J	`jnl`	Improved Robustness of Vision Transformer via PreLayerNorm in Patch Embedding. CoRR Bum Jun Kim, Hyeyeon Choi, Hyeonah Jang, Dong Gu Lee, Wonseok Jeong, Sang Woo Kim
2021	J	`jnl`	Weakly supervised power line detection algorithm using a recursive noisy label update with refined broken line segments. Expert Syst. Appl. Hyeyeon Choi, Gyogwon Koo, Bum Jun Kim, Sang Woo Kim
2020	J	`jnl`	Extending Class Activation Mapping Using Gaussian Receptive Field. CoRR Bum Jun Kim, Gyogwon Koo, Hyeyeon Choi, Sang Woo Kim
2019	Misc	`conf`	Real-time Power Line Detection Network using Visible Light and Infrared Images. IVCNZ Hyeyeon Choi, Gyogwon Koo, Bum Jun Kim, Sang Woo Kim