Deconfounded visual grounding

• المؤلفون الرئيسيون: HUANG, Jianqiang, QIN, Yu, QI, Jiaxin, SUN, Qianru, ZHANG, Hanwang
• التنسيق: text
• اللغة: English
• منشور في: Institutional Knowledge at Singapore Management University 2022
• الموضوعات: Computer Vision (CV); Artificial Intelligence and Robotics; Graphics and Human Computer Interfaces
• الوصول للمادة أونلاين: https://ink.library.smu.edu.sg/sis_research/7484; https://ink.library.smu.edu.sg/context/sis_research/article/8487/viewcontent/19983_Article_Text_23996_1_2_20220628.pdf

We focus on the confounding bias between language and location in the visual grounding pipeline, where we find that the bias is the major visual reasoning bottleneck. For example, the grounding process is usually a trivial languagelocation association without visual reasoning, e.g., grounding any la...