mlsanityData to 14 Oct 2026

RAFIC: Retrieval-Augmented Few-shot Image Classification

arXiv 2312.06868 ↗First posted 11 Dec 2023cs.CV cs.LGcited by 1

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 16 of its 21 references that are in the map. First posted on arXiv 11 Dec 2023.

Builds on

16 of 21 references.

References · 16

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,897
  3. 2022LAION-5B: An open large-scale dataset for training next generation image-text modelscited by 4,152
  4. 2017Prototypical Networks for Few-shot Learningcited by 3,015
  5. 2017Billion-scale similarity search with GPUscited by 2,497
  6. 2013Fine-Grained Visual Classification of Aircraftcited by 1,726
  7. 2022Tip-Adapter: Training-free Adaption of CLIP for Few-shot Classificationcited by 362
  8. 2019A Baseline for Few-Shot Image Classificationcited by 298
  9. 2017Data Augmentation Generative Adversarial Networkscited by 278
  10. 2018GAN Augmentation: Augmenting Training Data using Generative Adversarial Networkscited by 107
  11. 2022Retrieval Augmented Classification for Long-Tail Visual Recognitioncited by 106
  12. 2019Few-Shot Learning via Saliency-guided Hallucination of Samplescited by 49
4 more
  1. 2020Data Augmentation for Meta-Learningcited by 38
  2. 2020Unsupervised Meta-Learning through Latent-Space Interpolation in Generative Modelscited by 26
  3. 2020One-Shot Recognition of Manufacturing Defects in Steel Surfacescited by 13
  4. 2021Few-Shot Learning with Part Discovery and Augmentation from Unlabeled Imagescited by 8

Built on by

Cited by year

Citing papers per year: 2024: 1.

1 paper.

  1. 2024GarmentAligner: Text-to-Garment Generation via Retrieval-augmented Multi-level Correctionscited by 10

Similar, not cited

Close in wording, no citation either way

  1. 2026Few Shots Text to Image Retrieval: New Benchmarking Dataset and Optimization Methods
  2. 2024Retrieval-enriched zero-shot image classification in low-resource domains
  3. 2021LibFewShot: A Comprehensive Library for Few-shot Learning
  4. 2024Few-Shot Recognition via Stage-Wise Retrieval-Augmented Finetuning
  5. 2025Rethinking Few Shot CLIP Benchmarks: A Critical Analysis in the Inductive Setting
  6. 2024COBRA: COmBinatorial Retrieval Augmentation for Few-Shot Adaptation
  7. 2023Meta-Adapter: An Online Few-shot Learner for Vision-Language Model
  8. 2026Decompose, Compare, and Decide: Multimodal LLMs are Implicit Few-Shot Learners