Understanding Large Vision Models through a Lens of Signal Processing: Methodology and Applications

Research Project

Project/Area Number	25K15189
Research Category	Grant-in-Aid for Scientific Research (C)
Allocation Type	Multi-year Fund
Section	一般
Review Section	Basic Section 61010:Perceptual information processing-related
Research Institution	National Institute of Advanced Industrial Science and Technology
Principal Investigator	叶嘉星国立研究開発法人産業技術総合研究所, 計量標準総合センター, 主任研究員 (00803826)
Co-Investigator(Kenkyū-buntansha)	小林匠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, 上級主任研究員 (30443188) 李志遠国立研究開発法人産業技術総合研究所, 計量標準総合センター, 上級主任研究員 (70509710)
Project Period (FY)	2025-04-01 – 2028-03-31
Project Status	Granted (Fiscal Year 2025)
Budget Amount *help	¥6,370,000 (Direct Cost: ¥4,900,000、Indirect Cost: ¥1,470,000) Fiscal Year 2027: ¥1,950,000 (Direct Cost: ¥1,500,000、Indirect Cost: ¥450,000) Fiscal Year 2026: ¥2,080,000 (Direct Cost: ¥1,600,000、Indirect Cost: ¥480,000) Fiscal Year 2025: ¥2,340,000 (Direct Cost: ¥1,800,000、Indirect Cost: ¥540,000)
Keywords	Neural networks / Signal processing / Computer vision / Large vision models / Physics
Outline of Research at the Start	To better comprehend large vision models (LVMs) and implement safeguards for the applications, this research aims to casting signal processing knowledge into analysis of LVMs on the basis of synthetic data. We aim to build novel methodology for XAI and expand the scope of LVMs for signal processing.