Overcoming Language Priors with Self-supervised Learning for Visual Question Answering

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 (e. g. , what color is the banana? ) based on the high-frequency answers (e. g. , yellow) ignoring image contents. Existing approaches tackle this problem by creating delicate models or introducing additional visual annotations to reduce question dependency and strengthen image dependency. However, they are still subject to the language prior problem since the data biases have not been fundamentally addressed. In this paper, we introduce a self-supervised learning framework to solve this problem. Concretely, we first automatically generate labeled data to balance the biased data, and then propose a self-supervised auxiliary task to utilize the balanced data to assist the VQA model to overcome language priors. Our method can compensate for the data biases by generating balanced data without introducing external annotations. Experimental results show that our method achieves state-of-the-art performance, improving the overall accuracy from 49. 50% to 57. 59% on the most commonly used benchmark VQA-CP v2. In other words, we can increase the performance of annotation-based methods by 16% without using external annotations. Our code is available on GitHub.

Authors

• Xi Zhu
• Zhendong Mao University of Science and Technology of China
• Chunxiao Liu Xiaomi AI Lab
• Peng Zhang
• Bin Wang Qihoo 360 AI Research
• Yongdong Zhang University of Science and Technology of China

Keywords

• Computer Vision: Language and Vision
• Computer Vision: Recognition: Detection, Categorization, Indexing, Matching, Retrieval, Semantic Interpretation