作者
Remi Cadene, Corentin Dancette, Matthieu Cord, Devi Parikh
发表日期
2019
期刊
Advances in neural information processing systems
卷号
32
简介
Visual Question Answering (VQA) is the task of answering questions about an image. Some VQA models often exploit unimodal biases to provide the correct answer without using the image information. As a result, they suffer from a huge drop in performance when evaluated on data outside their training set distribution. This critical issue makes them unsuitable for real-world settings.
学术搜索中的文章
R Cadene, C Dancette, M Cord, D Parikh - Advances in neural information processing systems, 2019