As the manager of the research team at Deeping Source Inc., I am proud to lead a group of talented individuals who are dedicated to developing innovative image anonymization and AI analytics solutions. Our team is currently focused on researching multi-camera object tracking, image anonymization, and quantization, with a particular emphasis on real-world applications.
I received my Ph.D. from the Robotics and Computer Vision Lab at KAIST, South Korea, where I worked under the supervision of Prof. Kweon In So. My research during this time focused on machine learning techniques that are robust and reliable. Prior to my Ph.D., I obtained my diploma in mechanical engineering from the Technical University Kaiserslautern, Germany, where I studied under the guidance of Prof. Naim Bajcinca.
I am passionate about using cutting-edge technology to solve real-world problems, and I am excited to see what the future holds.
Ph.D. in Electrical Engineering, 2017 - 2021
KAIST, South Korea
Diploma in Mechanical Engineering, 2017
Technical University Kaiserslautern, Germany
We propose Homography Attention Module (HAM) which is shown to boost the performance of existing end-to-end multiview detection approaches by utilizing a novel channel gate and spatial gate. Additionally, we propose Booster-SHOT, an end-to-end convolutional approach to multiview pedestrian detection incorporating our proposed HAM as well as elements from previous approaches such as view-coherent augmentation or stacked homography transformations.
Training a reconstruction attacker can successfully recover the original image of existing Adversarial Representation Learning (ARL) methods. We introduce a novel ARL method enhanced through low-pass filtering, limiting the available information amount to be encoded in the frequency domain.
This work presents empirical findings that stronger attacks actually transfer better for the general top-k attack success rate indicated by the interest class rank after attack.
This work sets out to investigate the adversarial vulnerability of the ViT and MLP-Mixer architectures and compare their performance with CNNs.
Despite its wide usage, the gain of enhanced robustness from attack simulation layer (ASL) is usually interpreted through the lens of augmentation, while our work explores this gain from a new perspective by disentangling the forward and backward propagation of such ASL.