Knowledge-Based Counterfactual Queries for Visual Question Answering
Preprint
Abstract
Visual Question Answering (VQA) has been a popular task that combines vision and language, with numerous relevant implementations in literature. Even though there are some attempts that approach explainability and robustness issues in VQA models, very few of them employ counterfactuals as a means of probing such challenges in a model-agnostic way. In this work, we propose a systematic method for explaining the behavior and investigating the robustness of VQA models through counterfactual perturbations. For this reason, we exploit structured knowledge bases to perform deterministic, optimal and controllable word-level replacements targeting the linguistic modality, and we then evaluate the model's response against such counterfactual inputs. Finally, we qualitatively extract local and global explanations based on counterfactual responses, which are ultimately proven insightful towards interpreting VQA model behaviors. By performing a variety of perturbation types, targeting different parts of speech of the input question, we gain insights to the reasoning of the model, through the comparison of its responses in different adversarial circumstances. Overall, we reveal possible biases in the decision-making process of the model, as well as expected and unexpected patterns, which impact its performance quantitatively and qualitatively, as indicated by our analysis.Keywords
All Related Versions
This publication has 32 references indexed in Scilit:
- A survey on knowledge-enhanced multimodal learningArtificial Intelligence Review, 2024
- Driving behavior explanation with multi-level fusionPattern Recognition, 2022
- A survey of methods, datasets and evaluation metrics for visual question answeringImage and Vision Computing, 2021
- From Recognition to Cognition: Visual Commonsense Reasoning2019
- Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question AnsweringInternational Journal of Computer Vision, 2018
- Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering2018
- Visual question answering: Datasets, algorithms, and future challengesComputer Vision and Image Understanding, 2017
- Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image AnnotationsInternational Journal of Computer Vision, 2017
- VQA: Visual Question AnsweringInternational Journal of Computer Vision, 2016
- Visual7W: Grounded Question Answering in Images2016