Despite most state-of-the-art models having achieved amazing performance in visual
question answering (VQA), they usually utilize biases to answer the question. Recently …

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 …

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 …

Most Visual Question Answering (VQA) models suffer from the language prior problem,
which is caused by inherent data biases. Specifically, VQA models tend to answer questions …

Today's VQA models still tend to capture superficial linguistic correlations in the training set
and fail to generalize to the test set with different QA distributions. To reduce these language …

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

Despite the advances in Visual Question Answering (VQA), many VQA models currently
suffer from language priors (ie generating answers directly from questions without using …

Models for Visual Question Answering (VQA) often rely on the spurious correlations, ie, the
language priors, that appear in the biased samples of training set, which make them brittle …

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

As a prevailing cross-modal reasoning task, Visual Question Answering (VQA) has achieved
impressive progress in the last few years, where the language bias is widely studied to learn …