Student or educator? Sign up with your school email and get 6 months of Pro free.
CoChat
Sign Up
Cited by 237

The DOI matches its Crossref record; 5 of the 5 references it cites were found in a registry or an index.

Few-Shot Learning via Saliency-Guided Hallucination of Samples

Open access
Zhang, Hongguang, Zhang, Jing, Koniusz, Piotr·2019·2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
DOI 10.1109/cvpr.2019.00288
Open this paper in CoChat — free account

Abstract

Learning new concepts from a few of samples is a standard challenge in computer vision. The main directions to improve the learning ability of few-shot training models include (i) a robust similarity learning and (ii) generating or hallucinating additional data from the limited existing samples. In this paper, we follow the latter direction and present a novel data hallucination model. Currently, most datapoint generators contain a specialized network (i.e., GAN) tasked with hallucinating new datapoints, thus requiring large numbers of annotated data for their training in the first place. In this paper, we propose a novel less-costly hallucination method for few-shot learning which utilizes saliency maps. To this end, we employ a saliency network to obtain the foregrounds and backgrounds of available image samples and feed the resulting maps into a two-stream network to hallucinate datapoints directly in the feature space from viable foreground-background combinations. To the best of our knowledge, we are the first to leverage saliency maps for such a task and we demonstrate their usefulness in hallucinating additional datapoints for few-shot learning. Our proposed network achieves the state of the art on publicly available datasets.

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.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1109/cvpr.2019.00288

Cites

5 of 5 references verified0 citation errors · 0 not checkable

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.

A few free checks a day · papers already verified open instantly · results are public

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

Show all 5 references

Research works printed but not linked: 41

  1. 10.1109/CVPR.2018.00760 · DOI · Paper page
  2. snell, 2017, Prototypical networks for few-shot learning, NIPS, 4077
  3. 10.1007/s11263-015-0816-y · DOI · Paper page
  4. 10.1145/2466715.2466733 · DOI
  5. wang, 2016, Saliency detection with recurrent fully convolutional networks, ECCV, 825
  6. vinyals, 2016, Matching networks for one shot learning, NIPS, 3630
  7. 10.1007/11744047_45 · DOI · Paper page
  8. sung, 2017, Learning to compare: Relation network for few-shot learning, CoRR 1711 06025
  9. harandi, 2017, Joint dimensionality reduction and metric learning: A geometric take, ICML, 14041413
  10. 10.1109/ICCV.2017.328 · DOI · Paper page
  11. 10.1109/CVPR.2017.563 · DOI · Paper page
  12. 10.1109/CVPR.2009.5206609 · DOI · Paper page
  13. koch, 2015, Siamese neural networks for one-shot image recognition, ICML Deep Learning Workshop, 2
  14. 10.1007/978-3-030-01270-0_48 · DOI
  15. koniusz, 2013, Higherorder Occurrence Pooling on Mid- and Low-level Features: Visual Concept Detection, Technical Report
  16. 10.1109/TPAMI.2016.2545667 · DOI
  17. koniusz, 2012, Comparison of MidLevel Feature Coding Approaches And Pooling Strategies in Visual Concept Detection, CVIU
  18. 10.1007/978-3-540-39935-3 · doi:10.1007/978-3-540-39935-3
  19. boureau, 2010, A Theoretical Analysis of Feature Pooling in Vision Algorithms, ICML
  20. munkhdalai, 2017, CoRR 1703 00837
  21. 10.1109/TIP.2015.2487833 · DOI · Paper page
  22. 10.1109/CVPR.2011.5995344 · DOI · Paper page
  23. ravi, 2017, Optimization as a model for few-shot learning, ICLRE
  24. 10.1007/978-3-642-33786-4_32 · DOI · Paper page
  25. 10.1109/TPAMI.2006.79 · DOI · Paper page
  26. 10.1109/CVPR.2005.117 · DOI
  27. fink, 2005, Object classification from a single example utilizing class relevance metrics, NIPS, 449
  28. 10.1109/CVPR.2013.111 · DOI · Paper page
  29. 10.1109/CVPR.2018.00941 · DOI
  30. 10.1109/CVPR.2018.00605 · DOI
  31. 10.1109/WACV.2019.00131 · DOI
  32. lake, 2011, One shot learning of simple visual concepts, CogSci
  33. 10.1109/CVPR.2014.360 · DOI · Paper page
  34. 10.1109/CVPR.2012.6247939 · DOI · Paper page
  35. zhang, 2018, mixup: Beyond empirical risk minimization, ICLRE
  36. 10.1073/pnas.092277599 · DOI · Paper page
  37. larochelle, 2008, Zero-data learning of new tasks, AAAI
  38. 10.1109/CVPR.2018.00800 · DOI
  39. 10.1109/CVPR.2000.855856 · DOI · Paper page
  40. zhang, 2018, Model selection for generalized zero-shot learning, ECCV, 198
  41. 10.1109/CVPR.2007.383047 · DOI · Paper page

Cited by

See all 237

Metadata

Authors
Zhang, H., Zhang, J., & Koniusz, P.
Venue
2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Publisher
IEEE
Published
2019-06
Pages
2765-2774
ISSN
1063-6919 (ISSN-L)
DOI
10.1109/cvpr.2019.00288
OpenAlex
W2963350370
Cited by
237
References
5
FWCI
15.43
Type
conference paper
Language
en
Open access
green
Licence

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: Few-Shot Learning via Saliency-Guided Hallucination of Samples. https://app.cochat.ai/papers/10.1109/cvpr.2019.00288
The paper
Zhang, H., Zhang, J., & Koniusz, P. (2019). Few-Shot Learning via Saliency-Guided Hallucination of Samples. 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). https://doi.org/10.1109/cvpr.2019.00288

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.