Suppressing Biased Samples for Robust VQA

• Published in: IEEE transactions on multimedia Vol. 24; pp. 3405 - 3415
• Main Authors: Ouyang, Ninglin, Huang, Qingbao, Li, Pijian, Cai, Yi, Liu, Bin, Leung, Ho-fung, Li, Qing
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 2022; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Annotations; Bias; Datasets; Image color analysis; Knowledge discovery; Language; Language Bias; Language Priors; Modules; Questions; Robust VQA; Sports; Training; Training data; Visual Question Answering; Visualization

Most existing visual question answering (VQA) models strongly rely on language bias to answer questions, i.e., they always tend to fit question-answer pairs on the train split and perform poorly on the test spilt when the answer distributions are different. This behavior makes them hard to be applie...