CVLGDec 11, 2023

RAFIC: Retrieval-Augmented Few-shot Image Classification

arXiv:2312.06868v1h-index: 3Has Code
Originality Incremental advance
AI Analysis

This addresses the problem of low accuracy in few-shot image classification for AI/ML researchers, presenting an incremental improvement through retrieval augmentation.

The paper tackles few-shot image classification by augmenting limited training examples with retrieved images, demonstrating that RAFIC markedly improves performance across two challenging datasets.

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.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes