Timezone: »
Visual Question Answering (VQA) deep-learning systems tend to capture superficial statistical correlations in the training data because of strong language priors and fail to generalize to test data with a significantly different question-answer (QA) distribution. To address this issue, we introduce a self-critical training objective that ensures that visual explanations of correct answers match the most influential image regions more than other competitive answer candidates. The influential regions are either determined from human visual/textual explanations or automatically from just significant words in the question and answer. We evaluate our approach on the VQA generalization task using the VQA-CP dataset, achieving a new state-of-the-art i.e. 49.5\% using textual explanations and 48.5\% using automatically
Author Information
Jialin Wu (UT Austin)
Ray Mooney (University of Texas at Austin)
Related Events (a corresponding poster, oral, or spotlight)
-
2019 Poster: Self-Critical Reasoning for Robust Visual Question Answering »
Thu Dec 12th 01:00 -- 03:00 AM Room East Exhibition Hall B + C
More from the Same Authors
-
2011 Workshop: Integrating Language and Vision »
Raymond Mooney · Trevor Darrell · Kate Saenko