Prototypical Networks for Few-shot Learning¶
Authors: Jake Snell, Kevin Swersky, Richard Zemel Year: 2017 Venue: NeurIPS 2017 Citations: 10,000+
Link¶
Summary¶
Introduces Prototypical Networks for few-shot learning. Classifies examples by computing distances to prototypes (class means in embedding space). Simple, intuitive approach to learning from few examples via metric learning.
Key Concepts¶
- Metric Learning: Learn embedding space where distances reflect similarity
- Prototypes: Class means in learned embedding space
- Few-Shot Learning: Classify with few examples per class
- Distance-Based Classification: Assign to nearest prototype
- Episodic Training: Train on tasks sampling from class distribution
- Transductive Setting: Use query set statistics during testing
Impact¶
- 10,000+ citations
- Simple and intuitive few-shot learning approach
- Strong baseline for few-shot classification
- Influenced many metric learning approaches
- Practical and well-understood method
- Applications in zero-shot and few-shot scenarios
- Foundation for understanding similarity in learning
Key Results¶
- Few-shot classification with simple distance metric
- Competitive with more complex approaches
- Easy to understand and implement
- Good empirical performance
Related Papers¶
- Matching Networks (Vinyals et al., 2016)
- Relation Networks (Sung et al., 2018)
- Model-Agnostic Meta-Learning (Finn et al., 2017)
- Siamese Networks (Koch et al., 2015)