Meta-Baseline: Exploring Simple Meta-Learning for Few-Shot Learning
Abstract
Meta-learning has been the most common framework for few-shot learning in recent years. It learns the model from collections of few-shot classification tasks, which is believed to have a key advantage of making the training objective consistent with the testing objective. However, some recent works report that by training for whole-classification, i.e. classification on the whole label-set, it can get comparable or even better embedding than many meta-learning algorithms. The edge between these two lines of works has yet been underexplored, and the effectiveness of meta-learning in few-shot learning remains unclear. In this paper, we explore a simple process: meta-learning over a whole-classification pre-trained model on its evaluation metric. We observe this simple method achieves competitive performance to state-of-the-art methods on standard bench-marks. Our further analysis shed some light on understanding the trade-offs between the meta-learning objective and the whole-classification objective in few-shot learning. Our code is available at https://github.com/yinboc/few-shot-meta-baseline.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
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?
MoE models represent a significant innovation in neural network design, offering enhanced scalability and efficiency in training and inference.
“MoE models represent a significant innovation in neural network design, offering enhanced scalability and efficiency in training and inference [287], [288], [110].”
From From Google Gemini to OpenAI Q* (Q-Star): A Survey on Reshaping the Generative Artificial Intelligence (AI) Research Landscape (2025) · cites this paper as [288]
The router network in MoE layers plays a pivotal role in achieving load balance, which is fundamental to the stability and overall performance of MoE models.
“with the router network in MoE layers, responsible for selecting the appropriate experts for processing specific tokens, playing a pivotal role in achieving this balance, which is fundamental to the stability and overall performance of MoE models [293], [289], [288], [300], [110].”
From From Google Gemini to OpenAI Q* (Q-Star): A Survey on Reshaping the Generative Artificial Intelligence (AI) Research Landscape (2025) · cites this paper as [288]
Effective load balancing is essential in MoE models to guarantee a uniform distribution of computational load among experts.
“Effective load balancing is essential in MoE models to guarantee a uniform distribution of computational load among experts”
From From Google Gemini to OpenAI Q* (Q-Star): A Survey on Reshaping the Generative Artificial Intelligence (AI) Research Landscape (2025) · cites this paper as [288]
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 · see citing works
ImageNet Large Scale Visual Recognition Challenge
Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., Huang, Z., Karpathy, A., Khosla, A., Bernstein, M., et al. (2015) · International Journal of Computer Vision · doi:10.1007/s11263-015-0816-y · Cited by 39,380 · see citing works
Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
Ioffe, S., & Szegedy, C. (2015) · arXiv · doi:10.48550/arxiv.1502.03167 · Cited by 27,818 · see citing works
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 · see citing works
Prototypical Networks for Few-shot LearningPreprint
Snell, J., Swersky, K., & Zemel, R. S. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1703.05175 · Cited by 5,863 · see citing works
One-shot learning of object categories
Fei-Fei, L., Fergus, R., & Perona, P. (2006) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2006.79 · Cited by 3,029 · see citing works
Optimization as a Model for Few-Shot Learning
Ravi, S., & Larochelle, H. (2017) · International Conference on Learning Representations · Cited by 2,766 · see citing works
Meta-learning with memory-augmented neural networks
Santoro, A., Bartunov, S., Botvinick, M., Wierstra, D., & Lillicrap, T. (2016) · International Conference on Machine Learning · Cited by 1,504 · see citing works
Meta-Transfer Learning for Few-Shot Learning
Sun, Q., Liu, Y., Chua, T., & Schiele, B. (2019) · 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/cvpr.2019.00049 · Cited by 1,366 · see citing works
Meta-Learning With Differentiable Convex Optimization
Lee, K., Maji, S., Ravichandran, A., & Soatto, S. (2019) · 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/cvpr.2019.01091 · Cited by 1,351 · see citing works
Dynamic Few-Shot Visual Learning Without Forgetting
Gidaris, S., & Komodakis, N. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00459 · Cited by 1,128 · see citing works
A Simple Neural Attentive Meta-LearnerPreprint
Mishra, N., Rohaninejad, M., Chen, X., & Abbeel, P. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1707.03141 · Cited by 961 · see citing works
Rethinking 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 · see citing works
Meta-Learning for Semi-Supervised Few-Shot ClassificationPreprint
Ren, M., Triantafillou, E., Ravi, S., Snell, J., Swersky, K., Tenenbaum, J. B., Larochelle, H., & Zemel, R. S. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1803.00676 · Cited by 892 · see citing works
Few-Shot Image Recognition by Predicting Parameters from Activations
Qiao, S., Liu, C., Shen, W., & Yuille, A. (2018) · 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/cvpr.2018.00755 · Cited by 565 · see citing works
Low-Shot Learning with Imprinted Weights
Qi, H., Brown, M., & Lowe, D. G. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00610 · Cited by 539 · see citing works
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 · see citing works
Boosting Few-Shot Learning With Adaptive Margin Loss
Li, A., Huang, W., Xu, L., Feng, J., Li, Z., & Wang, L. (2020) · 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/cvpr42600.2020.01259 · Cited by 213 · see citing works
TAFE-Net: Task-Aware Feature Embeddings for Low Shot Learning
Wang, X., Yu, F., Wang, R., Darrell, T., & Gonzalez, J. E. (2019) · 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/cvpr.2019.00193 · Cited by 118 · see citing works
Self-citationRapid Adaptation with Conditionally Shifted NeuronsPreprint
Munkhdalai, T., Yuan, X., Mehri, S., et al. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1712.09926 · Cited by 106 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
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 · see citing works
McIntosh, T. R., Susnjak, T., Liu, T., Watters, P., Xu, D., Liu, D., & Halgamuge, M. N. (2025) · Technologies · doi:10.3390/technologies13020051 · Cited by 102 · see citing works
“It focuses on few-shot generalization, enabling AI to handle a wide range of tasks with minimal data, underlining its importance in developing versatile and adaptable AI systems [255], [256], [254], [257].”
Background
- Authors
- Chen, Y., Liu, Z., Xu, H., Darrell, T., & Wang, X.
- Affiliations
- University of California San Diego (US)
- University of California, Berkeley (US)
- Pennsylvania State University (US)
- Venue
- 2021 IEEE/CVF International Conference on Computer Vision (ICCV)
- Publisher
- IEEE
- Published
- 2021-10
- Pages
- 9042-9051
- OpenAlex
- W3205249428
- Cited by
- 503
- References
- 20
- Citations by year
- 2026: 59 · 2025: 112 · 2024: 147 · 2023: 95 · 2022: 69 · 2021: 17 · 2020: 4
- FWCI
- 37.88
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- IEEE/CVF International Conference on Computer Vision (ICCV) (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Domain Adaptation and Few-Shot Learning
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- Keywords
- meta-learning, few-shot learning, embedding learning
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
