# Few-Shot Learning with Embedded Class Models and Shot-Free Meta Training

arXiv: https://arxiv.org/abs/1905.04398 · HTML: https://mlsanity.com/paper/1905.04398/

## Key facts

- Cited by 57 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 May 2019.

## Built on by (most cited first, 30 of 57)

- [On the Role of Neural Collapse in Transfer Learning](https://mlsanity.com/paper/2112.15121/) (2021)
- [Relational Embedding for Few-Shot Classification](https://mlsanity.com/paper/2108.09666/) (2021)
- [Exploring Complementary Strengths of Invariant and Equivariant Representations for Few-Shot Learning](https://mlsanity.com/paper/2103.01315/) (2021)
- [Pareto Self-Supervised Training for Few-Shot Learning](https://mlsanity.com/paper/2104.07841/) (2021)
- [Orthogonal Projection Loss](https://mlsanity.com/paper/2103.14021/) (2021)
- [Partner-Assisted Learning for Few-Shot Image Classification](https://mlsanity.com/paper/2109.07607/) (2021)
- [Few-Shot Classification with Contrastive Learning](https://mlsanity.com/paper/2209.08224/) (2022)
- [MMG-Ego4D: Multi-Modal Generalization in Egocentric Action Recognition](https://mlsanity.com/paper/2305.07214/) (2023)
- [HyperShot: Few-Shot Learning by Kernel HyperNetworks](https://mlsanity.com/paper/2203.11378/) (2022)
- [Deep Metric Learning for Few-Shot Image Classification: A Review of Recent Developments](https://mlsanity.com/paper/2105.08149/) (2021)
- [Revisit Multimodal Meta-Learning through the Lens of Multi-Task Learning](https://mlsanity.com/paper/2110.14202/) (2021)
- [Few-Shot Learning with a Strong Teacher](https://mlsanity.com/paper/2107.00197/) (2021)
- [Few-Shot Learning Meets Transformer: Unified Query-Support Transformers for Few-Shot Classification](https://mlsanity.com/paper/2208.12398/) (2022)
- [Contrastive Prototype Learning with Augmented Embeddings for Few-Shot Learning](https://mlsanity.com/paper/2101.09499/) (2021)
- [SEGA: Semantic Guided Attention on Visual Prototype for Few-Shot Learning](https://mlsanity.com/paper/2111.04316/) (2021)
- [Adaptive Poincar'e Point to Set Distance for Few-Shot Classification](https://mlsanity.com/paper/2112.01719/) (2021)
- [Tree Structure-Aware Few-Shot Image Classification via Hierarchical Aggregation](https://mlsanity.com/paper/2207.06989/) (2022)
- [Adaptive Distribution Calibration for Few-Shot Learning with Hierarchical Optimal Transport](https://mlsanity.com/paper/2210.04144/) (2022)
- [The Role of Global Labels in Few-Shot Classification and How to Infer Them](https://mlsanity.com/paper/2108.04055/) (2021)
- [ECKPN: Explicit Class Knowledge Propagation Network for Transductive Few-shot Learning](https://mlsanity.com/paper/2106.08523/) (2021)
- [Label Hallucination for Few-Shot Classification](https://mlsanity.com/paper/2112.03340/) (2021)
- [Cap2Aug: Caption guided Image to Image data Augmentation](https://mlsanity.com/paper/2212.05404/) (2022)
- [DMN4: Few-shot Learning via Discriminative Mutual Nearest Neighbor Neural Network](https://mlsanity.com/paper/2103.08160/) (2021)
- [Few-shot Single-view 3D Reconstruction with Memory Prior Contrastive Network](https://mlsanity.com/paper/2208.00183/) (2022)
- [Federated Few-shot Learning](https://mlsanity.com/paper/2306.10234/) (2023)
- [Meta Learning on a Sequence of Imbalanced Domains with Difficulty Awareness](https://mlsanity.com/paper/2109.14120/) (2021)
- [Task Affinity with Maximum Bipartite Matching in Few-Shot Learning](https://mlsanity.com/paper/2110.02399/) (2021)
- [Generalization Bounds for Few-Shot Transfer Learning with Pretrained Classifiers](https://mlsanity.com/paper/2212.12532/) (2022)
- [What Makes for Effective Few-shot Point Cloud Classification?](https://mlsanity.com/paper/2304.00022/) (2023)
- [Supervised Momentum Contrastive Learning for Few-Shot Classification](https://mlsanity.com/paper/2101.11058/) (2021)

## Abstract (arXiv)

We propose a method for learning embeddings for few-shot learning that is suitable for use with any number of ways and any number of shots (shot-free). Rather than fixing the class prototypes to be the Euclidean average of sample embeddings, we allow them to live in a higher-dimensional space (embedded class models) and learn the prototypes along with the model parameters. The class representation function is defined implicitly, which allows us to deal with a variable number of shots per each class with a simple constant-size architecture. The class embedding encompasses metric learning, that facilitates adding new classes without crowding the class representation space. Despite being general and not tuned to the benchmark, our approach achieves state-of-the-art performance on the standard few-shot benchmark datasets.