Kim Wonjik ＫＩＭＷｏｎｊｉｋ

… Alternative Names

KIM Wonjik キムワンジク

Less

Researcher Number	20980478
Affiliation (Current)	2026: 国立研究開発法人産業技術総合研究所, 情報・人間工学領域, 研究員
Affiliation (based on the past Project Information) *help	2026: 国立研究開発法人産業技術総合研究所, 情報・人間工学領域, 研究員 2023 – 2024: 国立研究開発法人産業技術総合研究所, 情報・人間工学領域, 研究員
Review Section/Research Field	Principal Investigator Basic Section 61010:Perceptual information processing-related / 1001:Information science, computer engineering, and related fields
Keywords	Principal Investigator 少量学習 / データ特性を考慮した特徴量射影 / 畳み込み処理の自由度向上 / 人工知能モデルの表現力向上 / 特徴ベクトル制約 / kernel-level dropout / 正規化 / 深層学習 / バッチ内特徴量制約 / ランダムフォーカシング … More / カーネル単位ドロップアウト / 教師なしラベル統合 / 転移学習 / 人工知能 Less

Research Projects
(2 results)
Research Products
(6 results)

上位・下位概念の多層構造を用いた医療AIの効率的転移と知識創出戦略の開発Principal Investigator
- Principal Investigator
  
  KIM Wonjik
- Project Period (FY)
  2026 – 2028
- Research Category
  
  Grant-in-Aid for Early-Career Scientists
- Review Section
  
  Basic Section 61010:Perceptual information processing-related
- Research Institution
  National Institute of Advanced Industrial Science and Technology
Development of a system for building high-performance artificial intelligence models with limited data and low computational costPrincipal Investigator
- Principal Investigator
  
  KIM Wonjik
- Project Period (FY)
  2023 – 2024
- Research Category
  
  Grant-in-Aid for Research Activity Start-up
- Review Section
  
  1001:Information science, computer engineering, and related fields
- Research Institution
  National Institute of Advanced Industrial Science and Technology

All 2024 2023

All Journal Article Presentation

[Journal Article] A Random Focusing Method with Jensen-Shannon Divergence for Improving Deep Neural Network Performance Ensuring Architecture Consistency2024
- Author(s)
  Kim Wonjik
- Journal Title
  
  Neural Processing Letters
  
  Volume: 56 Issue: 4
- DOI
  10.1007/s11063-024-11668-z
- Peer Reviewed / Open Access
- Data Source
  KAKENHI-PROJECT-23K19985
[Journal Article] Deep metric learning with in-batch feature vector constraints and unsupervised label integration2024
- Author(s)
  Kim Wonjik
- Journal Title
  
  Evolutionary Intelligence
  
  Volume: 18 Issue: 1
- DOI
  10.1007/s12065-024-00990-z
- Peer Reviewed / Open Access
- Data Source
  KAKENHI-PROJECT-23K19985
[Journal Article] A Novel Approach to Deep Metric Learning with In-Batch Feature Vector Constraint2024
- Author(s)
  Wonjik Kim
- Journal Title
  
  ICIAI2024 Conference Proceedings
  
  Volume: -
- Data Source
  KAKENHI-PROJECT-23K19985
[Journal Article] Deformable element-wise dynamic convolution2023
- Author(s)
  Kim Wonjik、Tanaka Masayuki、Sasaki Yoko、Okutomi Masatoshi
- Journal Title
  
  Journal of Electronic Imaging
  
  Volume: 32 Issue: 05
- DOI
  10.1117/1.jei.32.5.053029
- Peer Reviewed
- Data Source
  KAKENHI-PROJECT-23K19985
[Presentation] A Novel Approach to Deep Metric Learning with In-Batch Feature Vector Constraint2024
- Author(s)
  Wonjik Kim
- Organizer
  2024 the 8th International Conference on Innovation in Artificial Intelligence
- Data Source
  KAKENHI-PROJECT-23K19985
[Presentation] Kernel-Level Dropout for the Convolution Process in Deep Learning2024
- Author(s)
  KIM Wonjik
- Organizer
  2024 IEEE 17th International Symposium on Embedded Multicore/Many-core Systems-on-Chip (MCSoC)
- Int'l Joint Research
- Data Source
  KAKENHI-PROJECT-23K19985

Kim Wonjik ＫＩＭ Ｗｏｎｊｉｋ

KIM Wonjik キム ワンジク

Research Projects

Research Products

上位・下位概念の多層構造を用いた医療AIの効率的転移と知識創出戦略の開発Principal Investigator

Principal Investigator

Project Period (FY)

Research Category

Review Section

Research Institution

Development of a system for building high-performance artificial intelligence models with limited data and low computational costPrincipal Investigator

Principal Investigator

Project Period (FY)

Research Category

Review Section

Research Institution

[Journal Article] A Random Focusing Method with Jensen-Shannon Divergence for Improving Deep Neural Network Performance Ensuring Architecture Consistency2024

Author(s)

Journal Title

DOI

Data Source

[Journal Article] Deep metric learning with in-batch feature vector constraints and unsupervised label integration2024

Author(s)

Journal Title

DOI

Data Source

[Journal Article] A Novel Approach to Deep Metric Learning with In-Batch Feature Vector Constraint2024

Author(s)

Journal Title

Data Source

[Journal Article] Deformable element-wise dynamic convolution2023

Author(s)

Journal Title

DOI

Data Source

[Presentation] A Novel Approach to Deep Metric Learning with In-Batch Feature Vector Constraint2024

Author(s)

Organizer

Data Source

[Presentation] Kernel-Level Dropout for the Convolution Process in Deep Learning2024

Author(s)

Organizer

Data Source

Kim Wonjik ＫＩＭＷｏｎｊｉｋ

KIM Wonjik キムワンジク