Z-Score Normalization, Hubness, and Few-Shot Learning
The DOI matches its Crossref record; 9 of the 9 references it cites were found in a registry or an index.
Abstract
The goal of few-shot learning (FSL) is to recognize a set of novel classes with only few labeled samples by exploiting a large set of abundant base class samples. Adopting a meta-learning framework, most recent FSL methods meta-learn a deep feature embedding network, and during inference classify novel class samples using nearest neighbor in the learned high-dimensional embedding space. This means that these methods are prone to the hubness problem, that is, a certain class prototype becomes the nearest neighbor of many test instances regardless which classes they belong to. However, this problem is largely ignored in existing FSL studies. In this work, for the first time we show that many FSL methods indeed suffer from the hubness problem. To mitigate its negative effects, we further propose to employ z-score feature normalization, a simple yet effective trans-formation, during meta-training. A theoretical analysis is provided on why it helps. Extensive experiments are then conducted to show that with z-score normalization, the performance of many recent FSL methods can be boosted, resulting in new state-of-the-art on three benchmarks.
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
Chen, L.-C., Papandreou, G., Kokkinos, I., Murphy, K., & Yuille, A. L. (2016) · arXiv · doi:10.48550/arxiv.1606.00915 · Cited by 22,392
Chen, L.-C., Papandreou, G., Kokkinos, I., Murphy, K., & Yuille, A. L. (2018) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2017.2699184 · Cited by 22,392
Unsupervised representation learning with deep convolutional generative adversarial networks
Radford, A., Metz, L., & Chintala, S. (2015) · arXiv · doi:10.48550/arxiv.1511.06434 · Cited by 12,235
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×
“Most recent few-shot learning (FSL) approaches [52, 35, 8, 47, 49, 30, 2, 59, 7, 63] are based on meta-learning using an episodic training strategy.”
BackgroundMethodLearning to Compare: Relation Network for Few-Shot Learning
Sung, F., Yang, Y., Zhang, L., Xiang, T., Torr, P. H. S., & Hospedales, T. M. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00131 · Cited by 5,816
Self-citationOn First-Order Meta-Learning Algorithms
Nichol, A., Achiam, J., & Schulman, J. (2018) · arXiv · doi:10.48550/arxiv.1803.02999 · Cited by 1,438 · cited 1×
“…samples into a shared task-agnostic metric space, [60, 31, 59, 44] further learn task-adaptive metric spaces for FSL. (2) Model-based methods [8, 29, 39] aim to learn good model initialization using the base classes, in order to quickly fine-tune them with a limited number of gradient update…”
MethodRethinking Few-Shot Image Classification: A Good Embedding is All You Need?
Tian, Y., Wang, Y., Krishnan, D., Tenenbaum, J. B., & Isola, P. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-58568-6_16 · Cited by 952
SimpleShot: Revisiting Nearest-Neighbor Classification for Few-Shot Learning
Wang, Y., Chao, W.-L., Weinberger, K. Q., & van der Maaten, L. (2019) · arXiv · doi:10.48550/arxiv.1911.04623 · Cited by 245 · cited 1×
“Additionally, the most related work to ours is SimpleShot [54], and we have the following differences: (1) We discover the existence of the hubness problem in FSL and provide a theoretical analysis while SimpleShot does neither.”
Background
Cited by
Anomaly Detection in Microservice-Based Systems
Nobre, J., Pires, E. J. S., & Reis, A. (2023) · Applied Sciences · doi:10.3390/app13137891 · Cited by 34
Metadata
- Authors
- Fei, N., Gao, Y., Lu, Z., & Xiang, T.
- Venue
- 2021 IEEE/CVF International Conference on Computer Vision (ICCV)
- Publisher
- IEEE
- Published
- 2021-10
- Pages
- 142-151
- OpenAlex
- W3204752714
- Cited by
- 189
- References
- 9
- FWCI
- 10.61
- Type
- conference paper
- Language
- en
- Open access
- closed
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: Z-Score Normalization, Hubness, and Few-Shot Learning. https://app.cochat.ai/papers/10.1109/iccv48922.2021.00021
- The paper
- Fei, N., Gao, Y., Lu, Z., & Xiang, T. (2021). Z-Score Normalization, Hubness, and Few-Shot Learning. 2021 IEEE/CVF International Conference on Computer Vision (ICCV). https://doi.org/10.1109/iccv48922.2021.00021
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.