Few-Shot Learning Through an Information Retrieval Lens

Abstract

Few-shot learning refers to understanding new concepts from only a few examples. We propose an information retrieval-inspired approach for this problem that is motivated by the increased importance of maximally leveraging all the available information in this low-data regime. We define a training objective that aims to extract as much information as possible from each training batch by effectively optimizing over all relative orderings of the batch points simultaneously. In particular, we view each batch point as a `query' that ranks the remaining ones based on its predicted relevance to them and we define a model within the framework of structured prediction to optimize mean Average Precision over these rankings. Our method achieves impressive results on the standard few-shot classification benchmarks while is also capable of few-shot retrieval.

References in corpus (1)

• Learning to Remember Rare Events

Cited by in corpus (6)

• SimpleShot: Revisiting Nearest-Neighbor Classification for Few-Shot Learning
• Recasting Gradient-Based Meta-Learning as Hierarchical Bayes
• NIPS - Not Even Wrong? A Systematic Review of Empirically Complete Demonstrations of Algorithmic Effectiveness in the Machine Learning and Artificial Intelligence Literature
• SynSig2Vec: Learning Representations from Synthetic Dynamic Signatures for Real-world Verification
• Towards Robust Pattern Recognition: A Review
• DAMSL: Domain Agnostic Meta Score-based Learning