Toward describing fine-grained details in computer vision through visual discrimination learning

Research Project

Project/Area Number	23K16945
Research Category	Grant-in-Aid for Early-Career Scientists
Allocation Type	Multi-year Fund
Review Section	Basic Section 61030:Intelligent informatics-related
Research Institution	Kyoto University
Principal Investigator	KASTNER MarcAurel 京都大学, 情報学研究科, 助教 (30966700)
Project Period (FY)	2023-04-01 – 2025-03-31
Project Status	Granted (Fiscal Year 2023)
Budget Amount *help	¥4,680,000 (Direct Cost: ¥3,600,000、Indirect Cost: ¥1,080,000) Fiscal Year 2024: ¥1,820,000 (Direct Cost: ¥1,400,000、Indirect Cost: ¥420,000) Fiscal Year 2023: ¥2,860,000 (Direct Cost: ¥2,200,000、Indirect Cost: ¥660,000)
Keywords	Computer Vision / Vision & Language / Fine-grained Data / Discrimination Learning
Outline of Research at the Start	Can a machine explain fine visual differences between two birds to a human? In this research, I develop a system to analyze fine-grained classes using visual discrimination learning. A main goal is to summarize visual characteristics specific to a class, generating a standalone textual description.