# Learning to Select Base Classes for Few-shot Classification

arXiv: https://arxiv.org/abs/2004.00315 · HTML: https://mlsanity.com/paper/2004.00315/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Apr 2020.

## Built on by (most cited first, 11 of 11)

- [Beyond Max-Margin: Class Margin Equilibrium for Few-shot Object Detection](https://mlsanity.com/paper/2103.04612/) (2021)
- [Generating Representative Samples for Few-Shot Classification](https://mlsanity.com/paper/2205.02918/) (2022)
- [TGDM: Target Guided Dynamic Mixup for Cross-Domain Few-Shot Learning](https://mlsanity.com/paper/2210.05392/) (2022)
- [Label Hallucination for Few-Shot Classification](https://mlsanity.com/paper/2112.03340/) (2021)
- [How Important is Importance Sampling for Deep Budgeted Training?](https://mlsanity.com/paper/2110.14283/) (2021)
- [Towards Enabling Meta-Learning from Target Models](https://mlsanity.com/paper/2104.03736/) (2021)
- [Few-shot Learning as Cluster-induced Voronoi Diagrams: A Geometric Approach](https://mlsanity.com/paper/2202.02471/) (2022)
- [A Discriminative Vectorial Framework for Multi-modal Feature Representation](https://mlsanity.com/paper/2103.05597/) (2021)
- [P3DC-Shot: Prior-Driven Discrete Data Calibration for Nearest-Neighbor Few-Shot Classification](https://mlsanity.com/paper/2301.00740/) (2023)
- [Meta Adaptive Task Sampling for Few-Domain Generalization](https://mlsanity.com/paper/2305.15644/) (2023)
- [What Makes Good Few-shot Examples for Vision-Language Models?](https://mlsanity.com/paper/2405.13532/) (2024)

## Abstract (arXiv)

Few-shot learning has attracted intensive research attention in recent years. Many methods have been proposed to generalize a model learned from provided base classes to novel classes, but no previous work studies how to select base classes, or even whether different base classes will result in different generalization performance of the learned model. In this paper, we utilize a simple yet effective measure, the Similarity Ratio, as an indicator for the generalization performance of a few-shot model. We then formulate the base class selection problem as a submodular optimization problem over Similarity Ratio. We further provide theoretical analysis on the optimization lower bound of different optimization methods, which could be used to identify the most appropriate algorithm for different experimental settings. The extensive experiments on ImageNet, Caltech256 and CUB-200-2011 demonstrate that our proposed method is effective in selecting a better base dataset.