English

RAFIC: Retrieval-Augmented Few-shot Image Classification

Computer Vision and Pattern Recognition 2023-12-13 v1 Machine Learning

Abstract

Few-shot image classification is the task of classifying unseen images to one of N mutually exclusive classes, using only a small number of training examples for each class. The limited availability of these examples (denoted as K) presents a significant challenge to classification accuracy in some cases. To address this, we have developed a method for augmenting the set of K with an addition set of A retrieved images. We call this system Retrieval-Augmented Few-shot Image Classification (RAFIC). Through a series of experiments, we demonstrate that RAFIC markedly improves performance of few-shot image classification across two challenging datasets. RAFIC consists of two main components: (a) a retrieval component which uses CLIP, LAION-5B, and faiss, in order to efficiently retrieve images similar to the supplied images, and (b) retrieval meta-learning, which learns to judiciously utilize the retrieved images. Code and data is available at github.com/amirziai/rafic.

Keywords

Cite

@article{arxiv.2312.06868,
  title  = {RAFIC: Retrieval-Augmented Few-shot Image Classification},
  author = {Hangfei Lin and Li Miao and Amir Ziai},
  journal= {arXiv preprint arXiv:2312.06868},
  year   = {2023}
}
R2 v1 2026-06-28T13:47:48.914Z