# Few-Shot Learning with Global Class Representations

arXiv: https://arxiv.org/abs/1908.05257 · HTML: https://mlsanity.com/paper/1908.05257/

## Key facts

- Cited by 44 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Aug 2019.

## Built on by (most cited first, 30 of 44)

- [A Comprehensive Survey of Few-shot Learning: Evolution, Applications, Challenges, and Opportunities](https://mlsanity.com/paper/2205.06743/) (2022)
- [Learning What Not to Segment: A New Perspective on Few-Shot Segmentation](https://mlsanity.com/paper/2203.07615/) (2022)
- [Generalized Few-Shot Object Detection without Forgetting](https://mlsanity.com/paper/2105.09491/) (2021)
- [HyperTransformer: Model Generation for Supervised and Semi-Supervised Few-Shot Learning](https://mlsanity.com/paper/2201.04182/) (2022)
- [Hybrid Relation Guided Set Matching for Few-shot Action Recognition](https://mlsanity.com/paper/2204.13423/) (2022)
- [Shallow Bayesian Meta Learning for Real-World Few-Shot Recognition](https://mlsanity.com/paper/2101.02833/) (2021)
- [MoLo: Motion-augmented Long-short Contrastive Learning for Few-shot Action Recognition](https://mlsanity.com/paper/2304.00946/) (2023)
- [Generalized and Incremental Few-Shot Learning by Explicit Learning and Calibration without Forgetting](https://mlsanity.com/paper/2108.08165/) (2021)
- [Meta Discovery: Learning to Discover Novel Classes given Very Limited Data](https://mlsanity.com/paper/2102.04002/) (2021)
- [MMG-Ego4D: Multi-Modal Generalization in Egocentric Action Recognition](https://mlsanity.com/paper/2305.07214/) (2023)
- [Meta-learning approaches for few-shot learning: A survey of recent advances](https://mlsanity.com/paper/2303.07502/) (2023)
- [Deep Metric Learning for Few-Shot Image Classification: A Review of Recent Developments](https://mlsanity.com/paper/2105.08149/) (2021)
- [Few-Shot Learning with Class Imbalance](https://mlsanity.com/paper/2101.02523/) (2021)
- [Few-Shot Learning with a Strong Teacher](https://mlsanity.com/paper/2107.00197/) (2021)
- [Sparse Spatial Transformers for Few-Shot Learning](https://mlsanity.com/paper/2109.12932/) (2021)
- [HyRSM++: Hybrid Relation Guided Temporal Set Matching for Few-shot Action Recognition](https://mlsanity.com/paper/2301.03330/) (2023)
- [MetaNODE: Prototype Optimization as a Neural ODE for Few-Shot Learning](https://mlsanity.com/paper/2103.14341/) (2021)
- [Few-Shot Learning by Integrating Spatial and Frequency Representation](https://mlsanity.com/paper/2105.05348/) (2021)
- [Architecture, Dataset and Model-Scale Agnostic Data-free Meta-Learning](https://mlsanity.com/paper/2303.11183/) (2023)
- [Few-Shot Object Detection by Attending to Per-Sample-Prototype](https://mlsanity.com/paper/2109.07734/) (2021)
- [CAD: Co-Adapting Discriminative Features for Improved Few-Shot Classification](https://mlsanity.com/paper/2203.13465/) (2022)
- [Few-shot Action Recognition with Captioning Foundation Models](https://mlsanity.com/paper/2310.10125/) (2023)
- [MalProtect: Stateful Defense Against Adversarial Query Attacks in ML-based Malware Detection](https://mlsanity.com/paper/2302.10739/) (2023)
- [Prototype Completion for Few-Shot Learning](https://mlsanity.com/paper/2108.05010/) (2021)
- [Local Propagation for Few-Shot Learning](https://mlsanity.com/paper/2101.01480/) (2021)
- [Dizygotic Conditional Variational AutoEncoder for Multi-Modal and Partial Modality Absent Few-Shot Learning](https://mlsanity.com/paper/2106.14467/) (2021)
- [DiffKendall: A Novel Approach for Few-Shot Learning with Differentiable Kendall's Rank Correlation](https://mlsanity.com/paper/2307.15317/) (2023)
- [Subspace Prototype Guidance for Mitigating Class Imbalance in Point Cloud Semantic Segmentation](https://mlsanity.com/paper/2408.10537/) (2024)
- [Few-shot Partial Multi-view Learning](https://mlsanity.com/paper/2105.02046/) (2021)
- [StratDef: Strategic Defense Against Adversarial Attacks in ML-based Malware Detection](https://mlsanity.com/paper/2202.07568/) (2022)

## Abstract (arXiv)

In this paper, we propose to tackle the challenging few-shot learning (FSL) problem by learning global class representations using both base and novel class training samples. In each training episode, an episodic class mean computed from a support set is registered with the global representation via a registration module. This produces a registered global class representation for computing the classification loss using a query set. Though following a similar episodic training pipeline as existing meta learning based approaches, our method differs significantly in that novel class training samples are involved in the training from the beginning. To compensate for the lack of novel class training samples, an effective sample synthesis strategy is developed to avoid overfitting. Importantly, by joint base-novel class training, our approach can be easily extended to a more practical yet challenging FSL setting, i.e., generalized FSL, where the label space of test data is extended to both base and novel classes. Extensive experiments show that our approach is effective for both of the two FSL settings.