Dong-Hwan Jang

I am a master's student at Seoul National University, Electrical and Computer Science Department, advised by Bohyung Han. I am currently at CMU as a visiting scholar, fully funded by Korea Government. I completed my Bachelors degree with Electrical and Computer Engineering & Technology Management from Seoul National University in 2020.

Email  /  CV  /  Google Scholar

I envision a machine that can dynamically adapt and evolve to the changing environment similar to our brain.

I believe current static neural networks call for the scale-up of their model size to compensate for the lack of adaptability, and make the models hard to be deployed in changing unstructured environments.
To address this issue, I am interested in dynamic neural networks that can make machines flexibly learn where to focus and evolve accordingly, like human brain.
My research interests include computer vision, machine learning, robotics, and neuroscience.

We propose DynOPool, a learnable resizing module that finds the optimal scale factors and receptive fields of intermediate feature maps.

We present DS4C South Korea Patient, Policy, and Provincial data (DS4C-PPP dataset). The dataset contains comprehensive data that could be used for causal analysis, such as per-patient symptom onset and confirmed date, travel frequency, hospital accessibility, and 61 preventative policies enacted in South Korea.

We propose spatially-variant motion deblur network based on the implicit neural representation. A spatially-variant deblurring network takes deformed features and their offsets as inputs.

We propose a novel framework of the dynamic spatially-adaptive modulation for image dehazing. The proposed algorithm introduces a selection module that conditionally determine the necessary modulation pathways in a bottom-up manner by providing a loss function optimizing both accuracy and efficiency.

We adaptively find the appropriate number of the residual blocks according to the severity and distortion type of the input in universal image restoration task.