The DOI matches its Crossref record; 76 of the 76 references it cites were found in a registry or an index.
VisQA: X-raying Vision and Language Reasoning in Transformers
Open accessAbstract
Visual Question Answering systems target answering open-ended textual questions given input images. They are a testbed for learning high-level reasoning with a primary use in HCI, for instance assistance for the visually impaired. Recent research has shown that state-of-the-art models tend to produce answers exploiting biases and shortcuts in the training data, and sometimes do not even look at the input image, instead of performing the required reasoning steps. We present VisQA, a visual analytics tool that explores this question of reasoning vs. bias exploitation. It exposes the key element of state-of-the-art neural models - attention maps in transformers. Our working hypothesis is that reasoning steps leading to model predictions are observable from attention distributions, which are particularly useful for visualization. The design process of VisQA was motivated by well-known bias examples from the fields of deep learning and vision-language reasoning and evaluated in two ways. First, as a result of a collaboration of three fields, machine learning, vision and language reasoning, and data analytics, the work lead to a better understanding of bias exploitation of neural models for VQA, which eventually resulted in an impact on its design and training through the proposition of a method for the transfer of reasoning patterns from an oracle model. Second, we also report on the design of VisQA, and a goal-oriented evaluation of VisQA targeting the analysis of a model decision process from multiple experts, providing evidence that it makes the inner workings of models accessible to users.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The check wasn’t confident either way, so it gives no verdict — never disputed.
In the citing paper
“In general, if aim to learn more explicit object concepts, more complex pretext losses will be used [204].”
From Multimodal learning with transformers: A survey (2023) · cites this paper as [204]
Experimental — accuracy not yet measuredIn the citing paper
“The RACE dataset [14] is a multiple-choice reading comprehension dataset built from English examinations used for benchmarking this task.”
From Interactive and Visual Prompt Engineering for Ad-hoc Task Adaptation With Large Language Models (2022) · cites this paper as [14]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, L., & Polosukhin, I. (2017) · arXiv · doi:10.48550/arxiv.1706.03762 · Cited by 120,404
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
Ren, S., He, K., Girshick, R., & Sun, J. (2017) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2016.2577031 · Cited by 73,472 · cited 3×
“While the input image itself does contain all clear pictures of the answer, the neural transformer model reasons over a list of objects detected by a first object detection and recognition module (Faster R-CNN [48]) which may output errors.”
InfluentialBERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2018) · arXiv · doi:10.48550/arxiv.1810.04805 · Cited by 73,173
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
Ren, S., He, K., Girshick, R., & Sun, J. (2015) · arXiv · doi:10.48550/arxiv.1506.01497 · Cited by 70,812 · cited 3×
“While the input image itself does contain all clear pictures of the answer, the neural transformer model reasons over a list of objects detected by a first object detection and recognition module (Faster R-CNN [48]) which may output errors.”
InfluentialBERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019) · Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers) · doi:10.18653/v1/n19-1423 · Cited by 54,325
Microsoft COCO: Common Objects in Context
Lin, T.-Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Dollár, P., & Zitnick, C. L. (2014) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-10602-1_48 · Cited by 45,460
PyTorch: An Imperative Style, High-Performance Deep Learning Library
Paszke, A., Gross, S., Massa, F., Lerer, A., Bradbury, J., Chanan, G., Killeen, T., Lin, Z., Gimelshein, N., Antiga, L., et al. (2019) · arXiv · doi:10.48550/arxiv.1912.01703 · Cited by 31,473 · cited 2×
“The user interface of V IS QA is implemented using D3 [6], and directly interacts with transformer models implemented in Pytorch [46], using JSON files through a python Flask server.”
MethodVisualizing and understanding convolutional networks
Zeiler, M. D., & Fergus, R. (2014) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-10590-1_53 · Cited by 15,839 · cited 1×
“Prior work focused on the analysis of image processing models, known as convolutional neuronal networks, by exposing their gradients over the inputted images [63].”
BackgroundWang, X., Girshick, R., Gupta, A., & He, K. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00813 · Cited by 11,596
How transferable are features in deep neural networks?
Yosinski, J., Clune, J., Bengio, Y., & Lipson, H. (2014) · arXiv · doi:10.48550/arxiv.1411.1792 · Cited by 6,061
Research works printed but not linked: 1
- 10.1109/CVPR.2019.00033 · DOI
Cited by
Multimodal learning with transformers: A survey
Xu, P., Zhu, X., & Clifton, D. A. (2023) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2023.3275156 · Cited by 1,072
“Depth to Binaural Audio [14], music piece & seed 3D motion to long-range future 3D motions [146], X-raying image & question to answer [244], video & text & audio to text [245]), and”
BackgroundExplainability for Large Language Models: A Survey
Zhao, H., Chen, H., Yang, F., Liu, N., Deng, H., Cai, H., Wang, S., Yin, D., & Du, M. (2024) · ACM Transactions on Intelligent Systems and Technology · doi:10.1145/3639372 · Cited by 681
“Some systems also allow users to manually modify attention weights to observe effects (Jaunet et al., 2021).”
BackgroundInteractive and Visual Prompt Engineering for Ad-hoc Task Adaptation With Large Language Models
Strobelt, H., Webson, A., Sanh, V., Hoover, B., Beyer, J., Pfister, H., & Rush, A. M. (2022) · IEEE Transactions on Visualization and Computer Graphics · doi:10.1109/tvcg.2022.3209479 · Cited by 204
“…expose the internals of a particular architecture (e.g., Transformers, RNNs, LSTMs) to understand how it encodes knowledge of the language [1,6,11,12,19,24,34,39,40]; (2) to explore and compare the behavior of a model’s internal distributions during text generation [9, 35]; and (3) to understand…”
AttentionViz: A Global View of Transformer Attention
Yeh, C. V., Chen, Y., Wu, A., Chen, C., Viégas, F. B., & WATTENBERG, M. P. (2023) · IEEE Transactions on Visualization and Computer Graphics · doi:10.1109/tvcg.2023.3327163 · Cited by 162
“Another system, VisQA [16], visualizes attention at different heads for visual question-answering tasks by showing heatmaps of language self-attention, vision self-attention, and language-vision cross-attention.”
BackgroundState of the Art of Visual Analytics for eXplainable Deep Learning
Rosa, B. L., Blasilli, G., Bourqui, R., Auber, D., Santucci, G., Capobianco, R., Bertini, E., Giot, R., & Angelini, M. (2023) · Computer Graphics Forum · doi:10.1111/cgf.14733 · Cited by 116
Metadata
- Authors
- Jaunet, T., Kervadec, C., Vuillemot, R., Antipov, G., Baccouche, M., & Wolf, C.
- Affiliations
- Laboratoire d'Informatique en Images et Systèmes d'Information (FR)
- École Centrale de Lyon (FR)
- Institute of Electrical and Electronics Engineers (US)
- Orange (France) (FR)
- Venue
- IEEE Transactions on Visualization and Computer Graphics
- Published
- 2022-01
- Volume
- 28
- Issue
- 1
- Pages
- 976-986
- ISSN
- 1077-2626 (ISSN-L)
- 1941-0506
- 2160-9306
- OpenAlex
- W3147788876
- Cited by
- 30
- References
- 74
- Citations by year
- 2026: 6 · 2025: 8 · 2024: 3 · 2023: 10 · 2022: 3
- FWCI
- 1.41
- Type
- journal article
- Language
- en
- Open access
- green
- arxiv.org
- Licence
- Locations
- IEEE Transactions on Visualization and Computer Graphics (publishedVersion)
- PubMed (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- HAL (submittedVersion, other-oa)
- arXiv (Cornell University)
- Funders
- Agence Nationale de la Recherche (ANR-20-CHIA-0018)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Explainable Artificial Intelligence (XAI)
- Physical Sciences › Computer Science › Computer Graphics and Computer-Aided Design › Data Visualization and Analytics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Multimodal Machine Learning Applications
- Keywords
- visual question answering, attention maps, transformer models, shortcut learning, vision-language reasoning, model interpretability, visual analytics tools, explainable AI
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: VisQA: X-raying Vision and Language Reasoning in Transformers. https://app.cochat.ai/papers/10.1109/tvcg.2021.3114683
- The paper
- Jaunet, T., Kervadec, C., Vuillemot, R., Antipov, G., Baccouche, M., & Wolf, C. (2022). VisQA: X-raying Vision and Language Reasoning in Transformers. IEEE Transactions on Visualization and Computer Graphics. https://doi.org/10.1109/tvcg.2021.3114683
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.