The DOI matches its Crossref record; 81 of the 83 references it cites were found in a registry or an index.
Causal Attention for Vision-Language Tasks
Abstract
We present a novel attention mechanism: Causal Attention (CATT), to remove the ever-elusive confounding effect in existing attention-based vision-language models. This effect causes harmful bias that misleads the attention module to focus on the spurious correlations in training data, damaging the model generalization. As the confounder is unobserved in general, we use the front-door adjustment to realize the causal intervention, which does not require any knowledge on the confounder. Specifically, CATT is implemented as a combination of 1) In-Sample Attention (IS-ATT) and 2) Cross-Sample Attention (CS-ATT), where the latter forcibly brings other samples into every IS-ATT, mimicking the causal intervention. CATT abides by the QK-V convention and hence can replace any attention module such as top-down attention and self-attention in Transformers. CATT improves various popular attention-based vision-language models by considerable margins. In particular, we show that CATT has great potential in large-scale pre-training, e.g., it can promote the lighter LXMERT [57], which uses fewer data and less computational power, comparable to the heavier UNITER [14]. Code is published in https://github.com/yangxuntu/lxmertcatt.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
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?
In the citing paper
“Meanwhile, overly compound pretraining objectives potentially upgrade the challenge of balancing among different loss terms, thus complicate the training optimization [199].”
From Multimodal learning with transformers: A survey (2023) · cites this paper as [199]
In the citing paper
“Some recently successful practice [9], [199], [205] used weakly aligned image-text pairs to perform pretraining, and achieve both competitive performance and zero-shot learning capability for image classification, image-text retrieval, and open-ended visual question answering, etc.”
From Multimodal learning with transformers: A survey (2023) · cites this paper as [199]
In the citing paper
“Some recent attempts [137], [199] study the use of weakly-aligned cross-modal supervision to train Transformers to learn the cross-modal interactions.”
From Multimodal learning with transformers: A survey (2023) · cites this paper as [199]
In the citing paper
“existing multimodal Transformer models [9], [199], [263] are superior only for specific MML tasks, as they are designed specifically for only a subset of specific tasks [137], [142], [212], [249], [260], [261], [265], [266].”
From Multimodal learning with transformers: A survey (2023) · cites this paper as [199]
In the citing paper
“As the learning scale expands exponentially, the training data become inevitably noisy and heterogeneous [9], [199], [263].”
From Multimodal learning with transformers: A survey (2023) · cites this paper as [199]
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
Jakubův, J., Chvalovský, K., Goertzel, Z., et al. (2023) · DROPS (Schloss Dagstuhl – Leibniz Center for Informatics) · doi:10.4230/lipics.itp.2023.19 · Cited by 76,648
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
BERT: 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
BERT: 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
(2014) · Cited by 33,419
End-to-End Object Detection with Transformers
Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., & Zagoruyko, S. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-58452-8_13 · Cited by 18,285
Neural Machine Translation by Jointly Learning to Align and Translate
Bahdanau, D., Cho, K., & Bengio, Y. (2014) · arXiv · doi:10.48550/arxiv.1409.0473 · Cited by 16,213
Wang, 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
Research works printed but not linked: 3
- luo, 2017, An Image Captioning Codebase in Pytorch
- hu, 2021, Distilling causal effect of data in classincremental learning
- radford, 2018, Improving language understanding by generative pre-training
Cited by
Sorted by citations
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
Counterfactual VQA: A Cause-Effect Look at Language Bias
Niu, Y., Tang, K., Zhang, H., Lu, Z., Hua, X., & Wen, J.-R. (2021) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr46437.2021.01251 · Cited by 464
Self-citationTransVG: End-to-End Visual Grounding with Transformers
Deng, J., Yang, Z., Chen, T., Zhou, W., & Li, H. (2021) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00179 · Cited by 424
Cross-Modal Causal Relational Reasoning for Event-Level Visual Question Answering
Liu, Y., Li, G., & Lin, L. (2023) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2023.3284038 · Cited by 373
Counterfactual Zero-Shot and Open-Set Visual Recognition
Yue, Z., Wang, T., Sun, Q., Hua, X., & Zhang, H. (2021) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr46437.2021.01515 · Cited by 221
Self-citation
Metadata
- Authors
- Yang, X., Zhang, H., Qi, G., & Cai, J.
- Affiliations
- Nanyang Technological University (SG)
- Monash University (AU)
- Venue
- 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
- Publisher
- IEEE
- Published
- 2021-06
- Pages
- 9842-9852
- ISSN
- 1063-6919 (ISSN-L)
- OpenAlex
- W3171353004
- Cited by
- 175
- References
- 83
- Citations by year
- 2026: 22 · 2025: 39 · 2024: 49 · 2023: 40 · 2022: 17 · 2021: 8
- FWCI
- 9.32
- Type
- conference paper
- Language
- en
- Open access
- closed
- Licence
- Locations
- IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Multimodal Machine Learning Applications
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Visual Attention and Saliency Detection
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Keywords
- causal attention, vision-language models, spurious correlations, confounding, front-door adjustment, causal intervention, LXMERT, pre-training, model generalization
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
