Deokki Hong

I am a graduate student in the Department of Artificial Intelligence at Yonsei University. I am interested in improving efficiency of neural networks by designing better networks(Neural Architecture Search; NAS). Additionally, I have done some researchs about neural network quantization, which is also for enhancing neural network efficiency.

Publication

• It’s All In the Teacher: Zero-Shot Quantization Brought Closer to the Teacher
  • Kanghyun Choi, Hyeyoon Lee, Deokki Hong, Joonsang Yu, Noseong Park, Youngsok Kim, Jinho Lee
    CVPR, 2022
    
• Hard-constrained Differentiable Co-Exploration Method for Neural Architectures and Hardware Accelerators
  • Deokki Hong, Kanghyun Choi, Hyeyoon Lee, Joonsang Yu, Noseong Park, Youngsok Kim, Jinho Lee
    DAC, 2022
    
• Qimera: Data-free Quantization with Synthetic Boundary Supporting Samples
  • Kanghyun Choi, Deokki Hong, Noseong Park, Youngsok Kim, Jinho Lee
    NeurIPS, 2021, Github, arXiv, Slides
    
• DANCE: Differentiable Accelerator/Network Co-Exploration
  • Kanghyun Choi¹, Deokki Hong¹, Hojae Yoon¹, Joonsang Yu, Youngsok Kim, Jinho Lee
    DAC, 2021, arXiv, Slides