Multimodal Prototypical Networks for Few-shot Learning
Open accessThe DOI matches its Crossref record; 12 of the 12 references it cites were found in a registry or an index.
Abstract
Although providing exceptional results for many computer vision tasks, state-of-the-art deep learning algorithms catastrophically struggle in low data scenarios. However, if data in additional modalities exist (e.g. text) this can compensate for the lack of data and improve the classification results. To overcome this data scarcity, we design a cross-modal feature generation framework capable of enriching the low populated embedding space in few-shot scenarios, leveraging data from the auxiliary modality. Specifically, we train a generative model that maps text data into the visual feature space to obtain more reliable prototypes. This allows to exploit data from additional modalities (e.g. text) during training while the ultimate task at test time remains classification with exclusively visual data. We show that in such cases nearest neighbor classification is a viable approach and outperform state-of-the-art single-modal and multimodal few-shot learning methods on the CUB-200 and Oxford-102 datasets.
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 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
Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
Finn, C., Abbeel, P., & Levine, S. (2017) · arXiv · doi:10.48550/arxiv.1703.03400 · Cited by 8,512 · cited 3×
“This method was proposed due to the observation that the update function of standard optimization algorithms like SGD is similar to the update of the cell state of a LSTM. Similarly, Finn et al. [9] suggested a model-agnostic meta-learning approach (MAML) that learns a model on base classes during a meta learning phas…”
BackgroundMethodDeep 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
Automated Flower Classification over a Large Number of Classes
Nilsback, M.-E., & Zisserman, A. (2008) · 2008 Sixth Indian Conference on Computer Vision, Graphics & Image Processing · doi:10.1109/icvgip.2008.47 · Cited by 3,442
Learning and Transferring Mid-level Image Representations Using Convolutional Neural Networks
Oquab, M., Bottou, L., Laptev, I., & Sivic, J. (2014) · 2014 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2014.222 · Cited by 3,150 · cited 1×
“Finetuning DNNs has been shown to be effective in a context where the big data assumption holds [25].”
StackGAN: Text to Photo-Realistic Image Synthesis with Stacked Generative Adversarial Networks
Zhang, H., Xu, T., Li, H., Zhang, S., Wang, X., Huang, X., & Metaxas, D. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.629 · Cited by 3,021 · cited 11×
“The last fully connected layer is employed as embedding space ϕ. Cross-Modal Generation For the text-to-image feature mapping we use a tcGAN architecture inspired by StackGAN++ [47].”
BackgroundMethodInfluentialGenerative Adversarial Text to Image Synthesis
Reed, S., Akata, Z., Yan, X., Logeswaran, L., Schiele, B., & Lee, H. (2016) · arXiv · doi:10.48550/arxiv.1605.05396 · Cited by 2,494
SIGNATURE VERIFICATION USING A “SIAMESE” TIME DELAY NEURAL NETWORK
BROMLEY, J., BENTZ, J. W., BOTTOU, L., GUYON, I., LECUN, Y., MOORE, C., SÄCKINGER, E., & SHAH, R. (1994) · Series in Machine Perception and Artificial Intelligence · doi:10.1142/9789812797926_0003 · Cited by 2,350
AttnGAN: Fine-Grained Text to Image Generation with Attentional Generative Adversarial Networks
Xu, T., Zhang, P., Huang, Q., Zhang, H., Gan, Z., Huang, X., & He, X. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00143 · Cited by 1,923
Feature Generating Networks for Zero-Shot Learning
Xian, Y., Lorenz, T., Schiele, B., & Akata, Z. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00581 · Cited by 1,080
Cited by
A Comprehensive Survey of Few-shot Learning: Evolution, Applications, Challenges, and Opportunities
Song, Y., Wang, T., Cai, P., Mondal, S. K., & Sahoo, J. P. (2023) · ACM Computing Surveys · doi:10.1145/3582688 · Cited by 721
“In few-shot visual classification tasks, the visual and semantic-based approaches [153], which try to use textual descriptions to generate additional training images, have a considerable advantage.”
BackgroundMethodRahate, A., Walambe, R., Ramanna, S., & Kotecha, K. (2022) · Information Fusion · doi:10.1016/j.inffus.2021.12.003 · Cited by 214
“GAN framework is used to generate visual features from the textual descriptions to balance the data in both modalities [107] to classify images using only visual data at test time.”
BackgroundMethodDeep learning for low-data drug discovery: Hurdles and opportunities
van Tilborg, D., Brinkmann, H., Criscuolo, E., Rossen, L., Özçelik, R., & Grisoni, F. (2024) · Current Opinion in Structural Biology · doi:10.1016/j.sbi.2024.102818 · Cited by 61
Metadata
- Authors
- Pahde, F., Puscas, M., Klein, T., & Nabi, M.
- Venue
- 2021 IEEE Winter Conference on Applications of Computer Vision (WACV)
- Publisher
- IEEE
- Published
- 2021-01
- Pages
- 2643-2652
- ISSN
- 2472-6737 (ISSN-L)
- OpenAlex
- W3103390191
- Cited by
- 110
- References
- 12
- FWCI
- 9.38
- 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
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Multimodal Prototypical Networks for Few-shot Learning. https://app.cochat.ai/papers/10.1109/wacv48630.2021.00269
- The paper
- Pahde, F., Puscas, M., Klein, T., & Nabi, M. (2021). Multimodal Prototypical Networks for Few-shot Learning. 2021 IEEE Winter Conference on Applications of Computer Vision (WACV). https://doi.org/10.1109/wacv48630.2021.00269
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.