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.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keytriantafillou2017few

Related papers

• Advancing Image Retrieval With Few-shot Learning And Relevance Feedback (2023)0.00
• Few Shots Text To Image Retrieval: New Benchmarking Dataset And Optimization Methods (2026)0.00
• Finding Significant Features For Few-shot Learning Using Dimensionality Reduction (2021)2.26
• RAFIC: Retrieval-augmented Few-shot Image Classification (2023)0.00
• Few-shot Prompting For Pairwise Ranking: An Effective Non-parametric Retrieval Model (2024)5.84
• Few-shot Recognition Via Stage-wise Retrieval-augmented Finetuning (2024)4.52
• Rankdnn: Learning To Rank For Few-shot Learning (2022)12.58
• Gmm-based Comprehensive Feature Extraction And Relative Distance Preservation For Few-shot Cross-modal Retrieval (2025)2.26