Question type-aware debiasing for test-time visual question answering model adaptation

• Main Authors: LIU, Jin, XIE, Jialong, ZHOU, Fengyu, HE, Shengfeng
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2024
• Subjects: Test-time adaptation; visual question answering; language debiasing; Artificial Intelligence and Robotics; Graphics and Human Computer Interfaces
• Online Access: https://ink.library.smu.edu.sg/sis_research/9804
• Institution: Singapore Management University

In Visual Question Answering (VQA), addressing language prior bias, where models excessively rely on superficial correlations between questions and answers, is crucial. This issue becomes more pronounced in real-world applications with diverse domains and varied question-answer distributions during...