Search Results for author: Do-Guk Kim

Found 4 papers, 1 papers with code

Proxyless Neural Architecture Adaptation for Supervised Learning and Self-Supervised Learning

no code implementations15 May 2022 Do-Guk Kim, Heung-Chang Lee

Recently, Neural Architecture Search (NAS) methods have been introduced and show impressive performance on many benchmarks.

Neural Architecture Search Self-Supervised Learning

Differentiable Neural Architecture Transformation for Reproducible Architecture Improvement

no code implementations15 Jun 2020 Do-Guk Kim, Heung-Chang Lee

Recently, Neural Architecture Search (NAS) methods are introduced and show impressive performance on many benchmarks.

Neural Architecture Search

Efficient Decoupled Neural Architecture Search by Structure and Operation Sampling

1 code implementation23 Oct 2019 Heung-Chang Lee, Do-Guk Kim, Bohyung Han

We propose a novel neural architecture search algorithm via reinforcement learning by decoupling structure and operation search processes.

Neural Architecture Search reinforcement-learning +1

Learning deep features for source color laser printer identification based on cascaded learning

no code implementations1 Nov 2017 Do-Guk Kim, Jong-Uk Hou, Heung-Kyu Lee

Color laser printers have fast printing speed and high resolution, and forgeries using color laser printers can cause significant harm to society.

Cannot find the paper you are looking for? You can Submit a new open access paper.