A Theoretical Analysis of the Number of Shots in Few-Shot Learning
arXiv:1909.11722
Abstract
Few-shot classification is the task of predicting the category of an example from a set of few labeled examples. The number of labeled examples per category is called the number of shots (or shot number). Recent works tackle this task through meta-learning, where a meta-learner extracts information from observed tasks during meta-training to quickly adapt to new tasks during meta-testing. In this formulation, the number of shots exploited during meta-training has an impact on the recognition performance at meta-test time. Generally, the shot number used in meta-training should match the one used in meta-testing to obtain the best performance. We introduce a theoretical analysis of the impact of the shot number on Prototypical Networks, a state-of-the-art few-shot classification method. From our analysis, we propose a simple method that is robust to the choice of shot number used during meta-training, which is a crucial hyperparameter. The performance of our model trained for an arbitrary meta-training shot number shows great performance for different values of meta-testing shot numbers. We experimentally demonstrate our approach on different few-shot classification benchmarks.
arXiv comment15 pages incl. appendix, 6 figures
References in corpus (6)
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
- Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
- Prototypical Networks for Few-shot Learning
- Meta-Learning with Latent Embedding Optimization
- Meta-Learning by Adjusting Priors Based on Extended PAC-Bayes Theory
- Infinite Mixture Prototypes for Few-Shot Learning
Cited by in corpus (4)
- MCML: A Novel Memory-based Contrastive Meta-Learning Method for Few Shot Slot Tagging
- Temporal Transductive Inference for Few-Shot Video Object Segmentation
- Theoretical bounds on estimation error for meta-learning
- Inconsistent Few-Shot Relation Classification via Cross-Attentional Prototype Networks with Contrastive Learning