RUBi: Reducing Unimodal Biases in Visual Question Answering

24 Jun 2019  ·  Remi Cadene, Corentin Dancette, Hedi Ben-Younes, Matthieu Cord, Devi Parikh ·

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: github.com/cdancette/rubi.bootstrap.pytorch read more

PDF Abstract
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Visual Question Answering VQA-CP RUBi Score 47.11 # 7
Visual Question Answering VQA v2 test-dev RUBi (ours) Accuracy 63.18 # 23

Methods


No methods listed for this paper. Add relevant methods here