Explanation vs Attention: A Two-Player Game to Obtain Attention for VQA

Patro, Badri N.; Anupriy,; Namboodiri, Vinay P.

doi:10.1609/aaai.v34i07.6858

Cited by 31 publications

(24 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Patro et al utilize adversarial training of the attention regions as a two-player game between attention and explanation. 16 We adopted a VQA model similar to what was proposed by Alipour et al 4 where the attention is derived from a transformer model. 17 Counterfactuals: Counterfactual examples have also been used to explain image classifiers.…”

Section: Related Workmentioning

confidence: 99%

Improving users' mental model with attention‐directed counterfactual edits

et al. 2021

View full text Add to dashboard Cite

In the domain of visual question answering (VQA), studies have shown improvement in users' mental model of the VQA system when they are exposed to examples of how these systems answer certain image‐question (IQ) pairs. In this work, we show that showing controlled counterfactual IQ examples are more effective at improving the mental model of users as compared to simply showing random examples. We compare a generative approach and a retrieval‐based approach to show counterfactual examples. We use recent advances in generative adversarial networks to generate counterfactual images by deleting and inpainting certain regions of interest in the image. We then expose users to changes in the VQA system's answer on those altered images. To select the region of interest for inpainting, we experiment with using both human‐annotated attention maps and a fully automatic method that uses the VQA system's attention values. Finally, we test the user's mental model by asking them to predict the model's performance on a test counterfactual image. We note an overall improvement in users' accuracy to predict answer change when shown counterfactual explanations. While realistic retrieved counterfactuals obviously are the most effective at improving the mental model, we show that a generative approach can also be equally effective.

show abstract

Section: Related Workmentioning

confidence: 99%

Improving users' mental model with attention‐directed counterfactual edits

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Some other works (such as DCN [39], BAN [40], and MCAN [41]) investigate "dense" co-attention that use bidirectional attention between images and questions. More recent works try to capture a more complex visual-textual information [42]- [45]. Our work instead tries to keep our approach as simple as possible by using three independently trained models to obtain the entropy.…”

Section: Related Workmentioning

confidence: 99%

An Entropy Clustering Approach for Assessing Visual Question Difficulty

et al. 2020

View full text Add to dashboard Cite

We propose a novel approach to identify the difficulty of visual questions for Visual Question Answering (VQA) without direct supervision or annotations to the difficulty. Prior works have considered the diversity of ground-truth answers of human annotators. In contrast, we analyze the difficulty of visual questions based on the behavior of multiple different VQA models. We propose to cluster the entropy values of the predicted answer distributions obtained by three different models: a baseline method that takes as input images and questions, and two variants that take as input images only and questions only. We use a simple k-means to cluster the visual questions of the VQA v2 validation set. Then we use state-of-the-art methods to determine the accuracy and the entropy of the answer distributions for each cluster. A benefit of the proposed method is that no annotation of the difficulty is required, because the accuracy of each cluster reflects the difficulty of visual questions that belong to it. Our approach can identify clusters of difficult visual questions that are not answered correctly by state-of-the-art methods. Detailed analysis on the VQA v2 dataset reveals that 1) all methods show poor performances on the most difficult cluster (about 10% accuracy), 2) as the cluster difficulty increases, the answers predicted by the different methods begin to differ, and 3) the values of cluster entropy are highly correlated with the cluster accuracy. We show that our approach has the advantage of being able to assess the difficulty of visual questions without ground-truth (i.e., the test set of VQA v2) by assigning them to one of the clusters. We expect that this can stimulate the development of novel directions of research and new algorithms.

show abstract

“…Li et al [26] has proposed an advanced method to generate sequence of conversion about an image. Patro et al [39] have proposed an adversarial method to improve explanation and attention using surrogate supervision method. In this work, we propose a collaborative correlated module to generate both answer and textual explanation of that answer which will be tightly correlated with each other.…”

Section: Related Workmentioning

confidence: 99%

Robust Explanations for Visual Question Answering

Patro¹,

Pate²,

Namboodiri³

2020

Preprint

View full text Add to dashboard Cite

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 https:// github.com/ DelTA-Lab-IITK/ CCM-WACV.

show abstract

Explanation vs Attention: A Two-Player Game to Obtain Attention for VQA

Cited by 31 publications

References 25 publications

Improving users' mental model with attention‐directed counterfactual edits

Improving users' mental model with attention‐directed counterfactual edits

An Entropy Clustering Approach for Assessing Visual Question Difficulty

Robust Explanations for Visual Question Answering

Contact Info

Product

Resources

About