NeurIPS 2019poster485 citations

RUBi: Reducing Unimodal Biases for Visual Question Answering

Remi Cadene, Corentin Dancette, Hedi Ben younes, Matthieu Cord, Devi Parikh

Abstract

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.

BibTeX
@inproceedings{NEURIPS2019_51d92be1,
 author = {Cadene, Remi and Dancette, Corentin and Ben younes, Hedi and Cord, Matthieu and Parikh, Devi},
 booktitle = {Advances in Neural Information Processing Systems},
 editor = {H. Wallach and H. Larochelle and A. Beygelzimer and F. d\textquotesingle Alch\'{e}-Buc and E. Fox and R. Garnett},
 pages = {},
 publisher = {Curran Associates, Inc.},
 title = {RUBi: Reducing Unimodal Biases for Visual Question Answering},
 url = {https://proceedings.neurips.cc/paper_files/paper/2019/file/51d92be1c60d1db1d2e5e7a07da55b26-Paper.pdf},
 volume = {32},
 year = {2019}
}