Publications

2024

Selected Publications

Eunseop Shin+, Incheon Cho+, Awais Muhammad, A F M Shahab Uddin, YounHo Jang, and Sung-Ho Bae*

G-SharP: Globally Shared Kernel with Pruning for Efficient CNNs, 

IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) 2024, 

(AI Top-conference) 

Junghun Cha+, Ali Haider+, Seoyun Yang, Hoeyeong Jin, Subin Yang, A. F.M.Shahab Uddin, Jaehyoung Kim, Soo Ye Kim*, Sung Ho Bae*

Descanning: From Scanned to the Original Images with a Color Correction Diffusion Model 

AAAI Conference on Artificial Intelligence (AAAI) 2024

(AI Top-conference) In collaboration with Adobe Research  

Muhammad Salman Ali, Maryam Qamar, Sung-Ho Bae*, Enzo Tartaglione*

Trimming the Fat: Efficient Compression of 3D Gaussian Splats through Pruning 

Accepted at BMVC 2024,

In collaboration with LTCI, Télécom Paris

Muhammad Salman Ali, Maryam Qamar, Sung-Ho Bae*, Enzo Tartaglione*

ELMGS: Enhancing memory and computation scaLability through coMpression for 3D Gaussian Splatting

Accepted at WACV 2025,

In collaboration with LTCI, Télécom Paris

2023

Selected Publications

Muhammad Salman Ali, Yeongwoong Kim, Sung-Chang Lim, Donghyun Kim, Chaoning Zhang, Maryam Qamar, Hui Yong Kim*, Sung-Ho Bae* 

Towards Efficient Image Compression Without Autoregressive Models,

Advances in Neural Information Processing Systems (NeurIPS) 2023, 

(AI Top-conference) 

Vo Hieu, Sung-Ho Bae, Lokwon Kim and Choong Seon Hong*,

MST-compression: Compressing and Accelerating Binary Neural Networks with Minimum Spanning Tree,   

International Conference on Computer Vision (ICCV) 2023

(AI Top-conference)

Awais Muhammad, Fahad Shamshad, and Sung-Ho Bae*,

Adversarial Attacks and Batch Normalization: A Batch Statistics Perspective,

IEEE Access, vol. 10, pp. 1-1, Mar. 2023.    

(IF=3.48) [pdf]

Jungheum Kang, Muhammad Salman Ali, Hyewon Jeong, Changkyun Choi, Younhee Kim, Se Yoon Jeong, Sung-Ho Bae*, Hui Yong Kim*

A Super-Resolution-based Feature Map Compression for Machine-oriented Video Coding,

IEEE Access, vol. 11, pp. 34198-34209, Mar. 2023.    

(IF=3.48) [pdf]

2022

Selected Publications

Qishi Dong+, Muhammad Awais+, Fengwei Zhou+, Chuanlong Xie, Tianyang Hu, Yongxin Yang, Sung-Ho Bae, Zhenguo Li*

ZooD: Exploiting Model Zoo for Out-of-Distribution Generalization,

Advances in Neural Information Processing Systems (NeurIPS) 2022

(AI Top-conference)  In collaboration with Huawei

 Younho Jang+,  Wheemyung Shin+, Joonbeom Kim, Simon Woo* and Sung-Ho Bae*,

GLAMD: Global and Local Attention Mask Distillation for Object Detectors,

European Conference on Computer Vision (ECCV) 2022, 

(AI Top-conference)  [pdf]

Md Tauhid Bin Iqbal, Byungyong Ryu, Ad ́ın Ram ́ırez Rivera, Farkhod Makhmudkhujaev, Oksam Chae, and Sung-Ho Bae*,

Facial Expression Recognition with Active Local Shape Pattern and Learned-Size Block Representations,

IEEE Transactions on Affective Computing, vol. 13, no. 3, pp. 1322-1336,  Sept. 2022. 

(IF=7.17) [pdf

Muhammad Awais and Sung-Ho Bae*

A Survey on Efficient Methods for Adversarial Robustness,

IEEE Access, vol. 10, pp. 118815-118830, Oct. 2022.    

(IF=3.48) [pdf]

Md. Tauhid Bin Iqbal, Abdun Muqeet, and Sung-Ho Bae*,

Visual Interpretation of CNN prediction through Layerwise Sequential Selection of Discernible Neurons,

IEEE Access, vol. 10, pp. 81988-82002, July. 2022.  

(IF=3.48) [pdf]

Joonhyun Jeong, Incheon Cho, Eunseop Shin, and Sung-Ho Bae*, 

A New Pointwise Convolution in Deep Neural Networks through Extremely Fast and Non Parametric Transforms,

IEEE Access, vol. 10, pp. 88251-88262, Aug. 2022.    

(IF=3.48) [pdf]

Joonki Bae+, Subin Yang+, and Sung-Ho Bae*, 

DenSE SwinHDR: SDRTV to HDRTV Conversion using Densely Connected Swin Transformer with Squeeze and Excitation Module,

IEEE Access, vol. 10, pp. 133969-133980, Dec. 2022.    

(IF=3.48) [pdf]

2021

Selected Publications

Muhammad Awais, Fengwei Zhou, Chuanlong Xie, Jiawei Li, Zhenguo Li, Sung-Ho Bae*, 

MixACM: Mixup-Based Robustness Transfer via Distillation of Activated Channel Maps,

Advances in Neural Information Processing Systems (NeurIPS) 2021, 

(AI Top-conference) In collaboration with Huawei [pdf]

Youmin Kim,  Jinbae Park, YounHo Jang, Muhammad Salman Ali, Tae-Hyun Oh and Sung-Ho Bae*,

Distilling Global and Local Logits with Densely Connected Relations,

International Conference on Computer Vision (ICCV) 2021, 

(AI Top-conference) [pdf]

Muhammad Awais, Fengwei Zhou, Hang Xu, Lanqing Hong, Ping Luo,  Zhenguo Li, Sung-Ho Bae*

Adversarial Robustness for Unsupervised Domain Adaptation,

International Conference on Computer Vision (ICCV) 2021, 

(AI Top-conference) In collaboration with Huawei [pdf]

A. F. M. Shahab Uddin, Mst. Sirazam Monira, Wheemyung Shin, TaeChoong Chung*, and Sung-Ho Bae*,

SaliencyMix: A Saliency Guided Data Augmentation Strategy for Better Regularization,

International Conference on Learning Representations (ICLR) 2021, 

(AI Top-conference) [pdf]

Muhammad Awais, Md Tauhid Iqbal, and Sung-Ho Bae*,

Revisiting Internal Covariant Shift for Batch Normalization,

IEEE Transactions on Neural Networks and Learning Systems, vol. 32, no. 11, Nov. 2021.

(AI Top-journal) (IF=10.45) [pdf]

Linh-Tam Tran, Muhammad Salman Ali, and Sung-Ho Bae*,

A Feature Fusion based Indicator for Training-free Neural Architecture Search,

IEEE Access, vol. 9, pp. 133914-133923, Sept. 2021.  

(IF=3.38) [pdf]

Kang-Ho Lee and Sung-Ho Bae*,

Compressing Neural Networks with Inter Prediction and Linear Transformation,

IEEE Access, vol. 9, pp. 69601-69608, Mar. 2021.  

(IF=3.75) [pdf]

Jiwon Hwang, A. F. M. Shahab Uddin, and Sung-Ho Bae*,

A Layer-wise Extreme Network Compression for Super Resolution,

IEEE Access, vol. 9, pp. 93998-94009, June 2021.

(IF=3.75) [pdf]

Youmin Kim, A. F. M. Shahab Uddin and Sung-Ho Bae*,

Local Augment: Utilizing Local Bias Property of Convolutional Neural Networks for Data Augmentation,

IEEE Access, vol. 9, pp. 15191-15199, Jan. 2021. 

(IF=3.75) [pdf]

Incheon Cho, Muhammad Salman Ali, and Sung-Ho Bae*,

Dynamic Structured Pruning with Novel Filter Importance and Leaky Masking based on Convolution and Batch Normalization Parameters,

IEEE Access, vol. 9, pp. 165005 - 165013, 30th, Nov. 2021.

(IF=3.38) [pdf]

Teerath Kumar, Jinbae Park, Muhammad Salman Ali, A F M Shahab Uddin, Jong Hwan Ko*, Sung-Ho Bae*,

Binary-Classifiers-Enabled Filters for Semi-Supervised Learning,

IEEE Access, , vol. 9, pp. 167663 - 167673, Nov. 2021.

(IF=3.38) [pdf

Young Jae Shin, Wheemyung Shin, Takashi Taniguchi, Kenji Watanabe, Philip Kim, and Sung-Ho Bae*,

Fast and Accurate Robotic Optical Detection of Exfoliated Graphene and Hexagonal Boron Nitride by Deep Neural Networks,

2D Materials, vol. 8, no. 3, pp.-, Apr. 2021. 

(IF=7.14) In collaboration with Harvard University [pdf]

2020

Selected Publications

Sung-Ho Bae, Jae-Hyeong Bae, Abdul Muqeet, Mst Sirazam Monira, Lok-Won Kim*,

Cost-Efficient Super-Resolution Hardware using Local Binary Pattern Classification and Linear Mapping for Real-Time 4K Conversion,

IEEE Access, vol. 8, pp. 224383-224393, Nov. 2020. 

(IF=3.75) [pdf]

Muhammad Salman Ali, Md Tauhid Bin Iqbal, Kang-Ho Lee, Abdul Muqeet, Seunghyun Lee, Lokwon Kim, Sung-Ho Bae*,

ERDNN: Error-Resilient Deep Neural Networks with a New Error Correction Layer and Piece-wise Rectified Linear Unit,

IEEE Access, vol. 8, pp. 158702-158711, Sept. 2020. 

(IF=3.75) [pdf]

Cam-Hao Hua,Thien Huynh-The, Sungyong Lee*, Sung-Ho Bae*,

Cross-Attentional Bracket-shaped Convolutional Network for Semantic Image Segmentation,

Information Sciences, vol. 539, pp. 277-294, June 2020. 

(IF=6.77) [pdf]

Gyungin Shin, Eunsu Park, Hyunjin Jeong, Harim Lee, and Sung-Ho Bae, Yong-Jae Moon*,

Generation of High-resolution Solar Pseudo-magnetograms from Ca II K Images by Deep Learning,

Astrophysical Journal Letters, vol. 895, no. 1, pp. 1-7, May 2020. 

(IF=7.70) [pdf]

Cam-Hao Hua, Kiyoung Kim, Thien Huynh-The, Jong In You, Seung-Young Yu, Thuong Le-Tien, Sung-Ho Bae*, and Sungyoung Lee*,

Convolutional Network with Twofold Feature Augmentation for Diabetic Retinopathy Recognition from Multi-modal Images,

IEEE Journal of Biomedical and Health Informatics, vol. 0, no. 0, pp. 2168-2194, Dec. 2020. 

(IF=5.22) [pdf]

SCI(E) Journals

International Conferences

2019

Selected Publications

Taeyoung Kim+, Eunsu Park+, Harim Lee, Sung-Ho Bae, Daye Lim, Soojeong Jang, Lokwon Kim, Il-Hyun Cho, Myungjin Choi, and Kyung-Suk Cho,Yong-Jae Moon*, (+: equal contributions) 

Generation of Solar Farside Magnetograms by Applying Deep Learning to STEREO/EUVI Data,

Nature Astronomy, vol. 3, pp. 372-400, Mar. 2019. 

(IF=11.52) [pdf]

A.F.M. Shahab Uddin, Tae-Choong Chung, Sung-Ho Bae*,

A Perceptually Inspired New Blind Image Denoising Method Using L1 and Perceptual Loss,

IEEE Access, vol. 7, pp. 90538-90549, July 2019. 

(IF=3.75) [pdf]

Abdul Muqeet, Md Tauhid Bin Iqbal, Sung-Ho Bae*,

Hybrid Residual Attention Network for Single Image Super Resolution,

IEEE Access, vol. 7, pp. 137020-137029, Sept. 2019. 

(IF=3.75) [pdf]

Cam-Hao Hua, Sungyoung Lee*, Kiyoung Kim, Gwang Hoon Park, Seung-Young Yu, Jaehun Bang, Thuong Le-Tien, Wajahat Ali Khan, Thien Huynh-The, Sung-Ho Bae*,

Bimodal Learning via Trilogy of Skip-connection Deep Networks for Diabetic Retinopathy Risk Progression Identification,

International Journal of Medical Informatics, vol. 132, Dec. 2019. 

(IF=3.59) [pdf]

SCI(E) Journals

2018

Selected Publications

Sehwan Ki, Sung-Ho Bae, Munchurl Kim* and Hyunsuk Ko,

Learning-based Just-Noticeable-Quantization-Distortion Modeling for Perceptual Video Coding,

IEEE Transactions on Image Processing, vol. 27, no. 7, pp. 3179-3193, July 2018. 

(IF=9.34) [pdf]

SCI(E) Journals

International Conferences

2013 - 2017

Selected Publications

Sung-Ho Bae and Munchurl Kim*,

DCT-QM: A DCT-based Quality Degradation Metric for Image Quality Optimization Problems,

IEEE Transactions on Image Processing, vol. 25, no. 10, pp. 4916-4930, May 2017. 

(2016 Qualcomm Innovation Award) (IF=9.34) [pdf]

Sung-Ho Bae and Munchurl Kim*,

A Novel Image Quality Assessment with Globally and Locally Consilient Visual Quality Perception,

IEEE Transactions on Image Processing, vol. 25, no. 5, pp. 2392-2406, May 2016. 

(2015 Samsung Electro-Mechanics Paper Award) (IF=9.34) [pdf]

Sung-Ho Bae and Munchurl Kim*,

HEVC-based Perceptually Adaptive Video Coding using a DCT-based Local Distortion Detection Probability Model,

IEEE Transactions on Image Processing, vol. 25, no. 7, pp. 3343-3357, May 2016. 

(2015 Qualcomm Innovation Award) (IF=9.34) [pdf]

Sung-Ho Bae and Munchurl Kim*,

A DCT-based Total JND Profile for Spatio-Temporal and Foveated Masking Effects,

IEEE Transactions on Circuits and Systems for Video Technology, vol. 27, no. 6, pp. 1196-1207, Mar. 2016. 

(IF=4.13) [pdf]

Jaeil Kim, Sung-Ho Bae, and Munchurl Kim*,

An HEVC-Compliant Perceptual Video Coding Scheme based on JND Models for Variable Block-sized Transform Kernels,

IEEE Transactions on Circuits and Systems for Video Technology, vol. 25, no. 11, pp. 1786-1800, Sept. 2015. 

(Best Encoder Optimization for HEVC Award in Grand Video Compression Challenge of PCS 2013)  

(IF=4.13) [pdf]

Sung-Ho Bae and Munchurl Kim*,

A Novel Generalized DCT-based JND Profile Based on an Elaborate CM-JND Model for Variable Block-Sized Transforms in Monochrome Images,

IEEE Transactions on Image Processing, vol. 23, no. 8, Aug. 2014. 

(2013 Qualcomm Innovation Award)  (IF=9.34) [pdf]

Sung-Ho Bae and Munchurl Kim*,

A Novel DCT-based JND Model for Luminance Adaptation Effect in DCT Frequency,

IEEE Signal Processing Letters, vol. 20, no. 9, pp. 893-896, Sept. 2013. 

(IF=4.18) [pdf]

Sung-Ho Bae, Jaeil Kim, Sukhee Cho, and Jin Soo Choi, Munchurl Kim*,

Assessments of Subjective Video Quality on HEVC-encoded 4K-UHD Video for Beyond-HDTV Broadcasting Services,

IEEE Transactions on Broadcasting, vol. 59, no. 2, pp. 209 - 222, June 2013. 

(IF=4.68) [pdf]

International Conferences