Computer Vision
 
Edit

Few-Shot Image Classification

201 papers with code • 88 benchmarks • 23 datasets

Few-Shot Image Classification is a computer vision task that involves training machine learning models to classify images into predefined categories using only a few labeled examples of each category (typically < 6 examples). The goal is to enable models to recognize and classify new images with minimal supervision and limited data, without having to train on large datasets. (typically < 6 examples)

( Image credit: Learning Embedding Adaptation for Few-Shot Learning )

Libraries

Use these libraries to find Few-Shot Image Classification models and implementations

Datasets

Subtasks

Unleashing the Power of Meta-tuning for Few-shot Generalization Through Sparse Interpolated Experts

szc12153/sparse_meta_tuning • • 13 Mar 2024

Conventional wisdom suggests parameter-efficient fine-tuning of foundation models as the state-of-the-art method for transfer learning in vision, replacing the rich literature of alternatives such as meta-learning.

3
13 Mar 2024
Paper
Code

BECLR: Batch Enhanced Contrastive Few-Shot Learning

stypoumic/beclr • • ICLR 2024

Learning quickly from very few labeled samples is a fundamental attribute that separates machines and humans in the era of deep representation learning.

9
04 Feb 2024
Paper
Code

RAFIC: Retrieval-Augmented Few-shot Image Classification

amirziai/rafic • • 11 Dec 2023

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.

5
11 Dec 2023
Paper
Code

Large Language Models are Good Prompt Learners for Low-Shot Image Classification

zhaohengz/llamp • 7 Dec 2023

Thus, we propose LLaMP, Large Language Models as Prompt learners, that produces adaptive prompts for the CLIP text encoder, establishing it as the connecting bridge.

3
07 Dec 2023
Paper
Code

Diversified in-domain synthesis with efficient fine-tuning for few-shot classification

vturrisi/disef • • 5 Dec 2023

Few-shot image classification aims to learn an image classifier using only a small set of labeled examples per class.

10
05 Dec 2023
Paper
Code

Are LSTMs Good Few-Shot Learners?

mikehuisman/lstm-fewshotlearning-oplstm • • 22 Oct 2023

Meta-learning overcomes this limitation by learning how to learn.

1
22 Oct 2023
Paper
Code

Context-Aware Meta-Learning

cfifty/CAML • • 17 Oct 2023

Large Language Models like ChatGPT demonstrate a remarkable capacity to learn new concepts during inference without any fine-tuning.

13
17 Oct 2023
Paper
Code

Subspace Adaptation Prior for Few-Shot Learning

mikehuisman/subspace-adaptation-prior • • 13 Oct 2023

Gradient-based meta-learning techniques aim to distill useful prior knowledge from a set of training tasks such that new tasks can be learned more efficiently with gradient descent.

3
13 Oct 2023
Paper
Code

SemiReward: A General Reward Model for Semi-supervised Learning

Westlake-AI/SemiReward • • 4 Oct 2023

The main challenge is how to distinguish high-quality pseudo labels against the confirmation bias.

42
04 Oct 2023
Paper
Code

Logarithm-transform aided Gaussian Sampling for Few-Shot Learning

ganatra-v/gaussian-sampling-fsl • • 28 Sep 2023

These methods rely on transforming the distributions of experimental data to approximate Gaussian distributions for their functioning.

0
28 Sep 2023
Paper
Code
Contact us on: hello@paperswithcode.com . Papers With Code is a free resource with all data licensed under CC-BY-SA.
Terms Data policy Cookies policy