# Generating and Evaluating Explanations of Attended and Error-Inducing Input Regions for VQA Models

arXiv: https://arxiv.org/abs/2103.14712 · HTML: https://mlsanity.com/paper/2103.14712/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 36 of its 52 references that are in the map.
- First posted on arXiv 26 Mar 2021.

## Builds on (most cited first, 30 of 36)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [Distributed Representations of Words and Phrases and their Compositionality](https://mlsanity.com/paper/1310.4546/) (2013)
- [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)
- [ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks](https://mlsanity.com/paper/1908.02265/) (2019)
- [Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering](https://mlsanity.com/paper/1707.07998/) (2017)
- [VisualBERT: A Simple and Performant Baseline for Vision and Language](https://mlsanity.com/paper/1908.03557/) (2019)
- [Explanation in Artificial Intelligence: Insights from the Social Sciences](https://mlsanity.com/paper/1706.07269/) (2017)
- [RISE: Randomized Input Sampling for Explanation of Black-box Models](https://mlsanity.com/paper/1806.07421/) (2018)
- [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)
- [Manipulating and Measuring Model Interpretability](https://mlsanity.com/paper/1802.07810/) (2018)
- [Multimodal Explanations: Justifying Decisions and Pointing to the Evidence](https://mlsanity.com/paper/1802.08129/) (2018)
- [Generating Visual Explanations](https://mlsanity.com/paper/1603.08507/) (2016)
- [Explaining Image Classifiers by Counterfactual Generation](https://mlsanity.com/paper/1807.08024/) (2018)
- [Watch-And-Help: A Challenge for Social Perception and Human-AI Collaboration](https://mlsanity.com/paper/2010.09890/) (2020)
- [Human Attention in Visual Question Answering: Do Humans and Deep Networks Look at the Same Regions?](https://mlsanity.com/paper/1606.03556/) (2016)
- [Grounding Visual Explanations](https://mlsanity.com/paper/1807.09685/) (2018)
- [Tips and Tricks for Visual Question Answering: Learnings from the 2017 Challenge](https://mlsanity.com/paper/1708.02711/) (2017)
- [Learning to Act Properly: Predicting and Explaining Affordances from Images](https://mlsanity.com/paper/1712.07576/) (2017)
- [Ask, Attend and Answer: Exploring Question-Guided Spatial Attention for Visual Question Answering](https://mlsanity.com/paper/1511.05234/) (2015)
- [Pythia v0.1: the Winning Entry to the VQA Challenge 2018](https://mlsanity.com/paper/1807.09956/) (2018)
- [Do Explanations make VQA Models more Predictable to a Human?](https://mlsanity.com/paper/1810.12366/) (2018)
- [Explicit Bias Discovery in Visual Question Answering Models](https://mlsanity.com/paper/1811.07789/) (2018)
- [Exploring Human-like Attention Supervision in Visual Question Answering](https://mlsanity.com/paper/1709.06308/) (2017)
- [U-CAM: Visual Explanation using Uncertainty based Class Activation Maps](https://mlsanity.com/paper/1908.06306/) (2019)
- [Show, Ask, Attend, and Answer: A Strong Baseline For Visual Question Answering](https://mlsanity.com/paper/1704.03162/) (2017)

## Built on by (most cited first, 2 of 2)

- [How explainable AI affects human performance: A systematic review of the behavioural consequences of saliency maps](https://mlsanity.com/paper/2404.16042/) (2024)
- [An Autoencoder and Vision Transformer-based Interpretability Analysis of the Differences in Automated Staging of Second and Third Molars](https://mlsanity.com/paper/2509.09911/) (2025)

## Abstract (arXiv)

Attention maps, a popular heatmap-based explanation method for Visual Question Answering (VQA), are supposed to help users understand the model by highlighting portions of the image/question used by the model to infer answers. However, we see that users are often misled by current attention map visualizations that point to relevant regions despite the model producing an incorrect answer. Hence, we propose Error Maps that clarify the error by highlighting image regions where the model is prone to err. Error maps can indicate when a correctly attended region may be processed incorrectly leading to an incorrect answer, and hence, improve users' understanding of those cases. To evaluate our new explanations, we further introduce a metric that simulates users' interpretation of explanations to evaluate their potential helpfulness to understand model correctness. We finally conduct user studies to see that our new explanations help users understand model correctness better than baselines by an expected 30% and that our proxy helpfulness metrics correlate strongly (ρ>0.97) with how well users can predict model correctness.