# Quantifying and Alleviating the Language Prior Problem in Visual Question Answering

arXiv: https://arxiv.org/abs/1905.04877 · HTML: https://mlsanity.com/paper/1905.04877/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 May 2019.

## Built on by (most cited first, 13 of 13)

- [MERIt: Meta-Path Guided Contrastive Learning for Logical Reasoning](https://mlsanity.com/paper/2203.00357/) (2022)
- [2D Human Pose Estimation: A Survey](https://mlsanity.com/paper/2204.07370/) (2022)
- [On Modality Bias Recognition and Reduction](https://mlsanity.com/paper/2202.12690/) (2022)
- [AdaVQA: Overcoming Language Priors with Adapted Margin Cosine Loss](https://mlsanity.com/paper/2105.01993/) (2021)
- [LPF: A Language-Prior Feedback Objective Function for De-biased Visual Question Answering](https://mlsanity.com/paper/2105.14300/) (2021)
- [X-GGM: Graph Generative Modeling for Out-of-Distribution Generalization in Visual Question Answering](https://mlsanity.com/paper/2107.11576/) (2021)
- [Answer Questions with Right Image Regions: A Visual Attention Regularization Approach](https://mlsanity.com/paper/2102.01916/) (2021)
- [Chairs Can be Stood on: Overcoming Object Bias in Human-Object Interaction Detection](https://mlsanity.com/paper/2207.02400/) (2022)
- [Distance Matters in Human-Object Interaction Detection](https://mlsanity.com/paper/2207.01869/) (2022)
- [REPT: Bridging Language Models and Machine Reading Comprehension via Retrieval-Based Pre-training](https://mlsanity.com/paper/2105.04201/) (2021)
- [Achieving Human Parity on Visual Question Answering](https://mlsanity.com/paper/2111.08896/) (2021)
- [Understanding and Testing Generalization of Deep Networks on Out-of-Distribution Data](https://mlsanity.com/paper/2111.09190/) (2021)
- [Leveraging Grammar Induction for Language Understanding and Generation](https://mlsanity.com/paper/2410.04878/) (2024)

## Abstract (arXiv)

Benefiting from the advancement of computer vision, natural language processing and information retrieval techniques, visual question answering (VQA), which aims to answer questions about an image or a video, has received lots of attentions over the past few years. Although some progress has been achieved so far, several studies have pointed out that current VQA models are heavily affected by the language prior problem, which means they tend to answer questions based on the co-occurrence patterns of question keywords (e.g., how many) and answers (e.g., 2) instead of understanding images and questions. Existing methods attempt to solve this problem by either balancing the biased datasets or forcing models to better understand images. However, only marginal effects and even performance deterioration are observed for the first and second solution, respectively. In addition, another important issue is the lack of measurement to quantitatively measure the extent of the language prior effect, which severely hinders the advancement of related techniques. In this paper, we make contributions to solve the above problems from two perspectives. Firstly, we design a metric to quantitatively measure the language prior effect of VQA models. The proposed metric has been demonstrated to be effective in our empirical studies. Secondly, we propose a regularization method (i.e., score regularization module) to enhance current VQA models by alleviating the language prior problem as well as boosting the backbone model performance. The proposed score regularization module adopts a pair-wise learning strategy, which makes the VQA models answer the question based on the reasoning of the image (upon this question) instead of basing on question-answer patterns observed in the biased training set. The score regularization module is flexible to be integrated into various VQA models.