Abstract Models for Visual Question Answering (VQA) are notorious for their tendency to rely
on dataset biases, as the large and unbalanced diversity of questions and concepts involved …

Existing unbiased visual question answering (VQA) models reduce the spurious correlation
between questions and answers to force the models to focus on visual information …

According to current research, one of the major challenges in Visual Question Answering
(VQA) models is the overdependence on language priors (and neglect of the visual …

Existing Visual Question Answering (VQA) models are often fragile and sensitive to input
variations. In this paper, we propose a novel approach to address this issue based on …

Abstract Despite Visual Question Answering (VQA) has realized impressive progress over
the last few years, today's VQA models tend to capture superficial linguistic correlations in …

Visual question answering (VQA) is designed to examine the visual-textual reasoning ability
of an intelligent agent. However, recent observations show that many VQA models may only …

Visual question answering requires a system to provide an accurate natural language
answer given an image and a natural language question. However, it is widely recognized …

Abstract While Visual Question Answering (VQA) has progressed rapidly, previous works
raise concerns about robustness of current VQA models. In this work, we study the …

In the task of Visual Question Answering (VQA), most state-of-the-art models tend to learn
spurious correlations in the training set and achieve poor performance in out-of-distribution …

Current Visual Question Answering (VQA) models mainly explore the statistical correlations
between answers and questions, which fail to capture the relationship between the visual …