Multi-Task Learning of Hierarchical Vision-Language Representation
Open accessThe DOI matches its Crossref record; 8 of the 8 references it cites were found in a registry or an index.
Abstract
It is still challenging to build an AI system that can perform tasks that involve vision and language at human level. So far, researchers have singled out individual tasks separately, for each of which they have designed networks and trained them on its dedicated datasets. Although this approach has seen a certain degree of success, it comes with difficulties of understanding relations among different tasks and transferring the knowledge learned for a task to others. We propose a multi-task learning approach that enables to learn vision-language representation that is shared by many tasks from their diverse datasets. The representation is hierarchical, and prediction for each task is computed from the representation at its corresponding level of the hierarchy. We show through experiments that our method consistently outperforms previous single-task-learning methods on image caption retrieval, visual question answering, and visual grounding. We also analyze the learned hierarchical representation by visualizing attention maps generated in our network.
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.
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 visual-semantic alignments for generating image descriptions
Karpathy, A., & Fei-Fei, L. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298932 · Cited by 4,902
VQA: Visual Question Answering
Antol, S., Agrawal, A., Lu, J., Mitchell, M., Batra, D., Zitnick, C. L., & Parikh, D. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.279 · Cited by 4,487
Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering
Goyal, Y., Khot, T., Summers-Stay, D., Batra, D., & Parikh, D. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.670 · Cited by 2,287
Multimodal Compact Bilinear Pooling for Visual Question Answering and Visual Grounding
Fukui, A., Park, D. H., Yang, D., Rohrbach, A., Darrell, T., & Rohrbach, M. (2016) · Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d16-1044 · Cited by 1,582
VQA: Visual Question Answering: www.visualqa.org
Agrawal, A., Lu, J., Antol, S., Mitchell, M., Zitnick, C. L., Parikh, D., & Batra, D. (2017) · International Journal of Computer Vision · doi:10.1007/s11263-016-0966-6 · Cited by 570
Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering
Goyal, Y., Khot, T., Agrawal, A., Summers-Stay, D., Batra, D., & Parikh, D. (2019) · International Journal of Computer Vision · doi:10.1007/s11263-018-1116-0 · Cited by 487 · cited 4×
“We use complementary image-question pairs contained in VQA 2.0 [13] for better analyses.”
BackgroundMethodInfluentialDas, A., Kottur, S., Gupta, K., Singh, A., Yadav, D., Moura, J. M. F., Parikh, D., & Batra, D. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.121 · Cited by 445 · cited 1×
“Vision-language representation learning Recently, studies of multi-modal tasks of vision and language have made significant progress, such as image captioning [2, 25], visual question answering [29, 36], visual grounding [40, 31], image caption retrieval [28, 16], and visual dialog [7].”
BackgroundLearning General Purpose Distributed Sentence Representations via Large Scale Multi-task Learning
Subramanian, S., Trischler, A., Bengio, Y., & Pal, C. J. (2018) · arXiv · doi:10.48550/arxiv.1804.00079 · Cited by 207
Cited by
Multimodal intelligence: Representation learning, information fusion, and applications
Zhang, C., Yang, Z., He, X., & Deng, L. (2020) · IEEE Journal of Selected Topics in Signal Processing · doi:10.1109/jstsp.2020.2987728 · Cited by 511
IMRAM: Iterative Matching With Recurrent Attention Memory for Cross-Modal Image-Text Retrieval
Chen, H., Ding, G., Liu, X., Lin, Z., Liu, J., & Han, J. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.01267 · Cited by 429
Multi-Task Learning with Deep Neural Networks: A Survey
Crawshaw, M. (2020) · arXiv · doi:10.48550/arxiv.2009.09796 · Cited by 428
“(Nguyen and Okatani, 2019) introduces an architecture for shared vision and language tasks by using dense co-attention layers (Nguyen and Okatani, 2018), in which tasks are organized into a hierarchy and low-level tasks are supervised at earlier layers in the network.”
Background12-in-1: Multi-Task Vision and Language Representation Learning
Lu, J., Goswami, V., Rohrbach, M., Parikh, D., & Lee, S. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.01045 · Cited by 410
Span-based Localizing Network for Natural Language Video Localization
Zhang, H., Sun, A., Jing, W., & Zhou, J. T. (2020) · Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/2020.acl-main.585 · Cited by 297
VLN↻BERT: A Recurrent Vision-and-Language BERT for Navigation
Hong, Y., Wu, Q., Qi, Y., Rodriguez-Opazo, C., & Gould, S. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.00169 · Cited by 264
“V&L Multi-Task Learning Instead of building a monolithic model for different V&L tasks, numbers of previous work explore multi-task learning with a unified model for utilising the common and the complementary knowledge to reduce the domain gap [31, 39, 42, 47, 33].”
BackgroundRahate, A., Walambe, R., Ramanna, S., & Kotecha, K. (2022) · Information Fusion · doi:10.1016/j.inffus.2021.12.003 · Cited by 214
“For the VQA task [170], a shared encoder with co-attention layers can be developed, and a separate decoder for each task in the MTL set-up.”
Method
Metadata
- Authors
- Nguyen, D.-K., & Okatani, T.
- Venue
- 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
- Publisher
- IEEE
- Published
- 2019-06
- Pages
- 10484-10493
- ISSN
- 1063-6919 (ISSN-L)
- OpenAlex
- W2903184186
- Cited by
- 55
- References
- 8
- FWCI
- 2.87
- Type
- conference paper
- Language
- en
- Open access
- green
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
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.