Jongseong Jang, Ph.D.
Researcher, LG AI Research
j.jang@lgresearch.ai
Research Interests
Vision and multimodal AI including,
Incremental learning
Transfer learning
Explanability in deeplearning
Data driven prediction
Experience
LG AI Research, Seoul, Korea (Apr. 2022 ~ present)
Medical AI
Multi-modal learning
Biomarker discovery
Prognosis predicition
LG AI Research, Toronto, ON, Canada(Feb. 2019 ~ Mar. 2022)
Enterprise AI, Vision inspection
AutoML & Reinforcement learning
Leaning theory for lifelong & transfer learning
Explainable AI(XAI)
Data driven prediction
Academy-Industry collaborative projects
LG CNS, Seoul, Korea (Jul. 2018 ~ Jan. 2019)
AI research for Inspection & Automation in Smart Factory
Center for Integration of Advanced Medicine Life Science Innovative Technologies(CAMIT), Kyushu University, Fukuoka, Japan (Jun. 2016 ~ Jun. 2018)
Deeplearning in medicine
Surgical Navigation, research and development
3D visualization of organs
Measuring of anatomic structures and movements
Machine learning for medical application
Institute of Intelligent Surgical Technology, Hanyang University, Seoul, Korea (Sep. 2014 ~ May 2016)
Medical software (viewing, rendering, processing medical images)
Surgical Navigation
System Integration
Education
Ph.D, Biomedical Engineering, Hanyang University, Seoul, Korea (2015)
Bs, Mechanical Engineering, Hanyang University, Seoul, Korea (2007)
Honors & Awards
3rd Prize in AutoCV1 of AutoDL challenge (Jul. 2019)
Team base_1
https://autodl.chalearn.org/
4th place in the Adversarial Vision Challenge (Robust Model Track) in NIPS2018 (Dec. 2018)
Team LAIR
https://www.crowdai.org/challenges/nips-2018-adversarial-vision-challenge-robust-model-track/leaderboards
Excellent Paper in Korea Software Congress(KSC) 2018 (Dec. 2018)
Paper: Comparing regularization methods for generalization of neural network against noises including adversarial attack (적대적 노이즈를 포함한 교란된 데이터에 대항하여 분류기의 일반화 성능을 확보하기 위한 정규화 방법)
Press reported: "3-modality fusion imaging may illuminate surgical guidance" (Apr. 2017)
https://www.healthimaging.com/image-category/molecular-imaging/3-modality-fusion-imaging-may-illuminate-surgical-guidance
Scholarship for post doctoral fellowship by Japan Society for the Promotion of Science (Jul. 2016 ~ May 2018)
Selected Publications
Journals
Zhang, Z., Jeong, Y., Jang, J., & Lee, C. G. (2022). A Pattern-driven Stochastic Degradation Model for the Prediction of Remaining Useful Life of Rechargeable Batteries. IEEE Transactions on Industrial Informatics, 18(12), 8586-8594
Lee, C., Jang, J., Lee, S., Kim, Y. S., Jo, H. J., & Kim, Y. (2020). Classification of femur fracture in pelvic X-ray images using meta-learned deep neural network. Scientific reports, 10(1), 1-12.
Na, Y. J., Jang, J. S., Lee, K. H., Yoon, Y. J., Chung, M. S., & Han, S. H. (2019). Thyroid cartilage loci and hyoid bone analysis using a video fluoroscopic swallowing study (VFSS). Medicine, 98(30).
Lee, C., Kim, Y., Kim, Y. S., & Jang, J. (2019). Automatic disease annotation from radiology reports using artificial intelligence implemented by a recurrent neural network. American Journal of Roentgenology, 212(4), 734-740.
Lee, C., Jang, J., Kim, H. W., Kim, Y. S., & Kim, Y. (2019). Three-dimensional analysis of acetabular orientation using a semi-automated algorithm. Computer Assisted Surgery, 24(1), 18-25.
Park, S., Jang, J., Kim, J., Kim, Y. S., & Kim, C. (2017). Real-time triple-modal photoacoustic, ultrasound, and magnetic resonance fusion imaging of humans. IEEE transactions on medical imaging, 36(9), 1912-1921.
Jang, J., Kim, H. W., So, B. R., & Kim, Y. S. (2015). Experimental study on restricting the robotic end-effector inside a lesion for safe telesurgery. Minimally Invasive Therapy & Allied Technologies, 24(6), 317-325.
Jang, J., Kim, H. W., & Kim, Y. S. (2014). Construction and verification of a safety region for brain tumor removal with a telesurgical robot system. Minimally Invasive Therapy & Allied Technologies, 23(6), 333-340.
Conference Proceedings
Lee, H. R., Sreenivasan, R. A., Jeong, Y., Jang, J., Shim, D., & Lee, C. G. Multi-policy Grounding and Ensemble Policy Learning for Transfer Learning with Dynamics Mismatch. In IJCAI-ECAI 2022
Sattarzadeh, S., Sudhakar, M., Plataniotis, K. N., Jang, J., Jeong, Y., & Kim, H. (2021, June). Integrated grad-CAM: Sensitivity-aware visual explanation of deep convolutional networks via integrated gradient-based scoring. In ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (pp. 1775-1779). IEEE.
Sudhakar, M., Sattarzadeh, S., Plataniotis, K. N., Jang, J., Jeong, Y., & Kim, H. (2021, June). Ada-SISE: adaptive semantic input sampling for efficient explanation of convolutional neural networks. In ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (pp. 1715-1719). IEEE.
Shim, D., Mai, Z., Jeong, J., Sanner, S., Kim, H., & Jang, J. (2020, February). Online Class-Incremental Continual Learning with Adversarial Shapley Value. In AAAI-21
Sattarzadeh, S., Sudhakar, M., Lem, A., Mehryar, S., Plataniotis, K. N., Jang, J., ... & Bae, K. (2020, February). Explaining Convolutional Neural Networks through Attribution-Based Input Sampling and Block-Wise Feature Aggregation. In AAAI-21
Park, S., Jang, J., Kim, J., Kim, Y. S., & Kim, C. (2017, April). Photoacoustic image-guided navigation system for surgery (Conference Presentation). In Photons Plus Ultrasound: Imaging and Sensing 2017 (Vol. 10064, p. 100640E). International Society for Optics and Photonics.
Jang, J., Kim, H. W., & Kim, Y. S. (2014, November). Co-segmentation of inter-subject brain magnetic resonance images. In 2014 11th International Conference on Ubiquitous Robots and Ambient Intelligence (URAI) (pp. 80-84). IEEE.
Jang, J., & Kim, Y. S. (2013, October). Safety management algorithm for telesurgical robot system for brain tumor surgery. In IEEE ISR 2013 (pp. 1-2). IEEE.
Workshops
Yoon, J., Kim, K., & Jang, J. (2019, October). Propagated Perturbation of Adversarial Attack for well-known CNNs: Empirical Study and its Explanation. In 2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW) (pp. 4226-4234). IEEE.
Jang, J. (2018, November) How to generate a robust image classifier against an adversarial attack: From the experience of NIPS 2018 Adversarial Vision Challenge. In NVIDIA AI Conference Seoul 2018. https://www.nvidia.com/ko-kr/ai-conference/old-agenda/