# Answer Questions with Right Image Regions: A Visual Attention Regularization Approach

arXiv: https://arxiv.org/abs/2102.01916 · HTML: https://mlsanity.com/paper/2102.01916/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 37 of its 53 references that are in the map.
- First posted on arXiv 3 Feb 2021.

## Builds on (most cited first, 30 of 37)

- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation](https://mlsanity.com/paper/1406.1078/) (2014)
- [Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering](https://mlsanity.com/paper/1612.00837/) (2016)
- [VQA: Visual Question Answering](https://mlsanity.com/paper/1505.00468/) (2015)
- [Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering](https://mlsanity.com/paper/1707.07998/) (2017)
- [Attention is not Explanation](https://mlsanity.com/paper/1902.10186/) (2019)
- [Don't Just Assume; Look and Answer: Overcoming Priors for Visual Question Answering](https://mlsanity.com/paper/1712.00377/) (2017)
- [Visual7W: Grounded Question Answering in Images](https://mlsanity.com/paper/1511.03416/) (2015)
- [Right for the Right Reasons: Training Differentiable Models by Constraining their Explanations](https://mlsanity.com/paper/1703.03717/) (2017)
- [Don't Take the Easy Way Out: Ensemble Based Methods for Avoiding Known Dataset Biases](https://mlsanity.com/paper/1909.03683/) (2019)
- [Hierarchical Question-Image Co-Attention for Visual Question Answering](https://mlsanity.com/paper/1606.00061/) (2016)
- [Stacked Attention Networks for Image Question Answering](https://mlsanity.com/paper/1511.02274/) (2015)
- [Multimodal Compact Bilinear Pooling for Visual Question Answering and Visual Grounding](https://mlsanity.com/paper/1606.01847/) (2016)
- [RUBi: Reducing Unimodal Biases in Visual Question Answering](https://mlsanity.com/paper/1906.10169/) (2019)
- [Counterfactual Samples Synthesizing for Robust Visual Question Answering](https://mlsanity.com/paper/2003.06576/) (2020)
- [Taking a HINT: Leveraging Explanations to Make Vision and Language Models More Grounded](https://mlsanity.com/paper/1902.03751/) (2019)
- [Visual Question Answering: A Survey of Methods and Datasets](https://mlsanity.com/paper/1607.05910/) (2016)
- [Human Attention in Visual Question Answering: Do Humans and Deep Networks Look at the Same Regions?](https://mlsanity.com/paper/1606.03556/) (2016)
- [Yin and Yang: Balancing and Answering Binary Visual Questions](https://mlsanity.com/paper/1511.05099/) (2015)
- [Overcoming Language Priors in Visual Question Answering with Adversarial Regularization](https://mlsanity.com/paper/1810.03649/) (2018)
- [COCO-CN for Cross-Lingual Image Tagging, Captioning and Retrieval](https://mlsanity.com/paper/1805.08661/) (2018)
- [On the Value of Out-of-Distribution Testing: An Example of Goodhart's Law](https://mlsanity.com/paper/2005.09241/) (2020)
- [MUREL: Multimodal Relational Reasoning for Visual Question Answering](https://mlsanity.com/paper/1902.09487/) (2019)
- [Ask, Attend and Answer: Exploring Question-Guided Spatial Attention for Visual Question Answering](https://mlsanity.com/paper/1511.05234/) (2015)
- [Where To Look: Focus Regions for Visual Question Answering](https://mlsanity.com/paper/1511.07394/) (2015)
- [Self-Critical Reasoning for Robust Visual Question Answering](https://mlsanity.com/paper/1905.09998/) (2019)
- [Removing Bias in Multi-modal Classifiers: Regularization by Maximizing Functional Entropies](https://mlsanity.com/paper/2010.10802/) (2020)
- [Overcoming Language Priors with Self-supervised Learning for Visual Question Answering](https://mlsanity.com/paper/2012.11528/) (2020)
- [Exploring Human-like Attention Supervision in Visual Question Answering](https://mlsanity.com/paper/1709.06308/) (2017)

## Built on by (most cited first, 9 of 9)

- [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)
- [Data Efficient Masked Language Modeling for Vision and Language](https://mlsanity.com/paper/2109.02040/) (2021)
- [VisFIS: Visual Feature Importance Supervision with Right-for-the-Right-Reason Objectives](https://mlsanity.com/paper/2206.11212/) (2022)
- [Guiding Visual Question Answering with Attention Priors](https://mlsanity.com/paper/2205.12616/) (2022)
- [Direct Visual Grounding by Directing Attention of Visual Tokens](https://mlsanity.com/paper/2511.12738/) (2025)
- [Zero-Shot Scene Graph Generation via Triplet Calibration and Reduction](https://mlsanity.com/paper/2309.03542/) (2023)
- [Deep Neural Networks for Visual Reasoning](https://mlsanity.com/paper/2209.11990/) (2022)
- [QIRL: Optimized Question-Image Relation Learning for Bias-Robust Visual Question Answering](https://mlsanity.com/paper/2504.03337/) (2025)

## Abstract (arXiv)

Visual attention in Visual Question Answering (VQA) targets at locating the right image regions regarding the answer prediction, offering a powerful technique to promote multi-modal understanding. However, recent studies have pointed out that the highlighted image regions from the visual attention are often irrelevant to the given question and answer, leading to model confusion for correct visual reasoning. To tackle this problem, existing methods mostly resort to aligning the visual attention weights with human attentions. Nevertheless, gathering such human data is laborious and expensive, making it burdensome to adapt well-developed models across datasets. To address this issue, in this paper, we devise a novel visual attention regularization approach, namely AttReg, for better visual grounding in VQA. Specifically, AttReg firstly identifies the image regions which are essential for question answering yet unexpectedly ignored (i.e., assigned with low attention weights) by the backbone model. And then a mask-guided learning scheme is leveraged to regularize the visual attention to focus more on these ignored key regions. The proposed method is very flexible and model-agnostic, which can be integrated into most visual attention-based VQA models and require no human attention supervision. Extensive experiments over three benchmark datasets, i.e., VQA-CP v2, VQA-CP v1, and VQA v2, have been conducted to evaluate the effectiveness of AttReg. As a by-product, when incorporating AttReg into the strong baseline LMH, our approach can achieve a new state-of-the-art accuracy of 60.00% with an absolute performance gain of 7.01% on the VQA-CP v2 benchmark dataset...