The DOI matches its Crossref record; 79 of the 85 references it cites were found in a registry or an index.
Thinking Fast and Slow: Efficient Text-to-Visual Retrieval with Transformers
Open accessAbstract
Our objective is language-based search of large-scale image and video datasets. For this task, the approach that consists of independently mapping text and vision to a joint embedding space, a.k.a. dual encoders, is attractive as retrieval scales and is efficient for billions of images using approximate nearest neighbour search. An alternative approach of using vision-text transformers with cross-attention gives considerable improvements in accuracy over the joint embeddings, but is often inapplicable in practice for large-scale retrieval given the cost of the cross-attention mechanisms required for each sample at test time. This work combines the best of both worlds. We make the following three contributions. First, we equip transformer-based models with a new fine-grained cross-attention architecture, providing significant improvements in retrieval accuracy whilst preserving scalability. Second, we introduce a generic approach for combining a Fast dual encoder model with our Slow but accurate transformer-based model via distillation and reranking. Finally, we validate our approach on the Flickr30K image dataset where we show an increase in inference speed by several orders of magnitude while having results competitive to the state of the art. We also extend our method to the video domain, improving the state of the art on the VATEX dataset.
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
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
“This has been studied for more challenging and fine-grained tasks (e.g., object detection [269], visual question answering [103], [106], [112], [263], and instance retrieval [222], [263]) by imposing region (semantic parts such as objects) level alignment.”
From Multimodal learning with transformers: A survey (2023) · cites this paper as [269]
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
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474
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
U-Net: Convolutional Networks for Biomedical Image Segmentation
Ronneberger, O., Fischer, P., & Brox, T. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-24574-4_28 · Cited by 99,404
Adam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946
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
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
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
Distributed Representations of Words and Phrases and their Compositionality
Mikolov, T., Sutskever, I., Chen, K., Corrado, G., & Dean, J. (2013) · arXiv · doi:10.48550/arxiv.1310.4546 · Cited by 24,533
SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation
Badrinarayanan, V., Kendall, A., & Cipolla, R. (2017) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2016.2644615 · Cited by 19,631
(2011) · Cited by 14,317
Research works printed but not linked: 4
- 10.1109/ICCV.2019.00054 · DOI
- 10.1109/CVPR42600.2020.01079 · DOI · Paper page
- daniel, 2017, Thinking Fast and Slow
- chen, 2017, Learning efficient object detection models with knowledge distillation, NIPS
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
Cross-Modal Implicit Relation Reasoning and Aligning for Text-to-Image Person Retrieval
Jiang, D., & Ye, M. (2023) · 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/cvpr52729.2023.00273 · Cited by 367
Perceiver IO: A General Architecture for Structured Inputs & OutputsPreprint
Jaegle, A., Borgeaud, S., Alayrac, J.-B., Doersch, C., Ionescu, C., Ding, X. D., Koppula, S., Zoran, D., Brock, A., Shelhamer, E., et al. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2107.14795 · Cited by 641
Self-citationX-Pool: Cross-Modal Language-Video Attention for Text-Video Retrieval
Gorti, S. K., Vouitsis, N., Ma, J., Golestan, K., Volkovs, M., Garg, A., & Yu, G. (2022) · 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/cvpr52688.2022.00495 · Cited by 261
Selva, J., Johansen, A. S., Escalera, S., Nasrollahi, K., Moeslund, T. B., & Clapés, A. (2023) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2023.3243465 · Cited by 192
Metadata
- Authors
- Miech, A., Alayrac, J.-B., Laptev, I., Sivic, J., & Zisserman, A.
- Affiliations
- Centre National de la Recherche Scientifique (FR)
- Venue
- 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
- Publisher
- IEEE
- Published
- 2021-06
- Pages
- 9821-9831
- ISSN
- 1063-6919 (ISSN-L)
- OpenAlex
- W3141362964
- Cited by
- 149
- References
- 85
- Citations by year
- 2026: 7 · 2025: 21 · 2024: 31 · 2023: 39 · 2022: 39 · 2021: 12
- FWCI
- 9.88
- Type
- conference paper
- Language
- en
- Open access
- green
- arxiv.org
- 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)
- arXiv (Cornell University) (submittedVersion)
- HAL (submittedVersion)
- arXiv (Cornell University)
- Funders
- European Regional Development Fund
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Multimodal Machine Learning Applications
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Image and Video Retrieval Techniques
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Image Retrieval and Classification Techniques
- Keywords
- text-to-image retrieval, video-text retrieval, cross-attention, dual-encoder models, approximate nearest neighbor search, knowledge distillation, re-ranking, inference efficiency, large-scale image retrieval, Flickr30k
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
