# Learning content and context with language bias for Visual Question Answering

arXiv: https://arxiv.org/abs/2012.11134 · HTML: https://mlsanity.com/paper/2012.11134/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Dec 2020.

## Built on by (most cited first, 7 of 7)

- [Robust Visual Question Answering: Datasets, Methods, and Future Challenges](https://mlsanity.com/paper/2307.11471/) (2023)
- [Visual Question Answering: A Survey on Techniques and Common Trends in Recent Literature](https://mlsanity.com/paper/2305.11033/) (2023)
- [Unveiling and Mitigating Bias in Audio Visual Segmentation](https://mlsanity.com/paper/2407.16638/) (2024)
- [X-GGM: Graph Generative Modeling for Out-of-Distribution Generalization in Visual Question Answering](https://mlsanity.com/paper/2107.11576/) (2021)
- [Language bias in Visual Question Answering: A Survey and Taxonomy](https://mlsanity.com/paper/2111.08531/) (2021)
- [An Empirical Study on the Language Modal in Visual Question Answering](https://mlsanity.com/paper/2305.10143/) (2023)
- [Overcoming Language Priors for Visual Question Answering Based on Knowledge Distillation](https://mlsanity.com/paper/2501.05690/) (2025)

## Abstract (arXiv)

Visual Question Answering (VQA) is a challenging multimodal task to answer questions about an image. Many works concentrate on how to reduce language bias which makes models answer questions ignoring visual content and language context. However, reducing language bias also weakens the ability of VQA models to learn context prior. To address this issue, we propose a novel learning strategy named CCB, which forces VQA models to answer questions relying on Content and Context with language Bias. Specifically, CCB establishes Content and Context branches on top of a base VQA model and forces them to focus on local key content and global effective context respectively. Moreover, a joint loss function is proposed to reduce the importance of biased samples and retain their beneficial influence on answering questions. Experiments show that CCB outperforms the state-of-the-art methods in terms of accuracy on VQA-CP v2.