# Robust Explanations for Visual Question Answering

arXiv: https://arxiv.org/abs/2001.08730 · HTML: https://mlsanity.com/paper/2001.08730/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Jan 2020.

## Built on by (most cited first, 14 of 14)

- [Toward Transparent AI: A Survey on Interpreting the Inner Structures of Deep Neural Networks](https://mlsanity.com/paper/2207.13243/) (2022)
- [A Review on Explainability in Multimodal Deep Neural Nets](https://mlsanity.com/paper/2105.07878/) (2021)
- [A Review on Methods and Applications in Multimodal Deep Learning](https://mlsanity.com/paper/2202.09195/) (2022)
- [On Explaining Multimodal Hateful Meme Detection Models](https://mlsanity.com/paper/2204.01734/) (2022)
- [Recent Advances and Trends in Multimodal Deep Learning: A Review](https://mlsanity.com/paper/2105.11087/) (2021)
- [Multimodal Explainable Artificial Intelligence: A Comprehensive Review of Methodological Advances and Future Research Directions](https://mlsanity.com/paper/2306.05731/) (2023)
- [CLEVR-X: A Visual Reasoning Dataset for Natural Language Explanations](https://mlsanity.com/paper/2204.02380/) (2022)
- [Chunk-aware Alignment and Lexical Constraint for Visual Entailment with Natural Language Explanations](https://mlsanity.com/paper/2207.11401/) (2022)
- [Measuring Faithful and Plausible Visual Grounding in VQA](https://mlsanity.com/paper/2305.15015/) (2023)
- [Sentence Attention Blocks for Answer Grounding](https://mlsanity.com/paper/2309.11593/) (2023)
- [Show Why the Answer is Correct! Towards Explainable AI using Compositional Temporal Attention](https://mlsanity.com/paper/2105.07141/) (2021)
- [PReGAN: Answer Oriented Passage Ranking with Weakly Supervised GAN](https://mlsanity.com/paper/2207.01762/) (2022)
- [Multimodal Rationales for Explainable Visual Question Answering](https://mlsanity.com/paper/2402.03896/) (2024)
- [A Framework for Generating Artificial Datasets to Validate Absolute and Relative Position Concepts](https://mlsanity.com/paper/2509.18177/) (2025)

## Abstract (arXiv)

In this paper, we propose a method to obtain robust explanations for visual question answering(VQA) that correlate well with the answers. Our model explains the answers obtained through a VQA model by providing visual and textual explanations. The main challenges that we address are i) Answers and textual explanations obtained by current methods are not well correlated and ii) Current methods for visual explanation do not focus on the right location for explaining the answer. We address both these challenges by using a collaborative correlated module which ensures that even if we do not train for noise based attacks, the enhanced correlation ensures that the right explanation and answer can be generated. We further show that this also aids in improving the generated visual and textual explanations. The use of the correlated module can be thought of as a robust method to verify if the answer and explanations are coherent. We evaluate this model using VQA-X dataset. We observe that the proposed method yields better textual and visual justification that supports the decision. We showcase the robustness of the model against a noise-based perturbation attack using corresponding visual and textual explanations. A detailed empirical analysis is shown. Here we provide source code link for our model urlhttps://github.com/DelTA-Lab-IITK/CCM-WACV.