RUBi: Reducing Unimodal Biases in Visual Question Answering

By Rémi Cadène, Corentin Dancette, Hedi Ben-Younes, Matthieu Cord, Devi Parikh. 2019

442 citations recorded by the source corpus.

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. We propose RUBi, a new learning strategy to reduce biases in any VQA model. It reduces the importance of the most biased examples, i.e. examples that can be correctly classified without looking at the image. It implicitly forces the VQA model to use the two input modalities instead of relying on statistical regularities between the question and the answer. We leverage a question-only model that captures the language biases by identifying when these unwanted regularities are used. It prevents the base VQA model from learning them by influencing its predictions. This leads to dynamically adjusting the loss in order to compensate for biases. We validate our contributions by surpassing the current state-of-the-art results on VQA-CP v2. This dataset is specifically designed to assess the robustness of VQA models when exposed to different question biases at test time than what was seen during training. Our code is available: this http URL

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Multimodal Learning, Question Answering & Reading Comprehension

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

  1. Jianfeng Gao
  2. Mohit Bansal
  3. Zhe Gan
  4. Percy Liang
  5. Yejin Choi
  6. Luke S. Zettlemoyer
  7. Yoshua Bengio
  8. Caiming Xiong

In Computer Vision and Pattern Recognition

  1. Luc Van Gool
  2. Dacheng Tao
  3. Trevor Darrell
  4. Xiaogang Wang
  5. Bernt Schiele
  6. Cordelia Schmid
  7. Ming-Hsuan Yang
  8. Andrew Zisserman

In Multimodal Learning

  1. Zhe Gan
  2. Linjie Li
  3. Hanwang Zhang
  4. Jingjing Liu
  5. Anton van den Hengel
  6. Damien Teney
  7. Jianfeng Gao
  8. Jianfei Cai

In Question Answering & Reading Comprehension

  1. Damien Teney
  2. Anton van den Hengel
  3. Xiaodong He
  4. Yonatan Belinkov
  5. Hanwang Zhang
  6. Radu Soricut
  7. Ehsan Abbasnejad
  8. Piyush Sharma

Citations in the corpus