Research Area:  Machine Learning

Abstract:

Visual question answering (VQA) is a challenging task, which has attracted more and more attention in the field of computer vision and natural language processing. However, the current visual question answering has the problem of language bias, which reduces the robustness of the model and has an adverse impact on the practical application of visual question answering. In this paper, we conduct a comprehensive review and analysis of this field for the first time, and classify the existing methods according to three categories, including enhancing visual information, weakening language priors, data enhancement and training strategies. At the same time, the relevant representative methods are introduced, summarized and analyzed in turn. The causes of language bias are revealed and classified. Secondly, this paper introduces the datasets mainly used for testing, and reports the experimental results of various existing methods. Finally, we discuss the possible future research directions in this field.

Keywords:  
Visual Question Answering
Natural language processing
Computer vision
Machine Learning
Deep Learning

Author(s) Name:  Desen Yuan

Publisher name:  arXiv:2111.08531

DOI:  10.48550/arXiv.2111.08531

Volume Information:  

Paper Link:   https://arxiv.org/abs/2111.08531