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

Most implemented papers

Most implemented Social Latest No code

ELEVATER: A Benchmark and Toolkit for Evaluating Language-Augmented Visual Models

computer-vision-in-the-wild/cvinw_readings • 19 Apr 2022

In general, these language-augmented visual models demonstrate strong transferability to a variety of datasets and tasks.

8
Paper
Code

Meta-Learning with Differentiable Convex Optimization

kjunelee/MetaOptNet • • CVPR 2019

We propose to use these predictors as base learners to learn representations for few-shot learning and show they offer better tradeoffs between feature size and performance across a range of few-shot recognition benchmarks.

7
Paper
Code

Charting the Right Manifold: Manifold Mixup for Few-shot Learning

nupurkmr9/S2M2_fewshot • • 28 Jul 2019

A recent regularization technique - Manifold Mixup focuses on learning a general-purpose representation, robust to small changes in the data distribution.

7
Paper
Code

Meta-Learning with Implicit Gradients

aravindr93/imaml_dev • • NeurIPS 2019

By drawing upon implicit differentiation, we develop the implicit MAML algorithm, which depends only on the solution to the inner level optimization and not the path taken by the inner loop optimizer.

6
Paper
Code

SimpleShot: Revisiting Nearest-Neighbor Classification for Few-Shot Learning

mileyan/simple_shot • • 12 Nov 2019

Few-shot learners aim to recognize new object classes based on a small number of labeled training examples.

6
Paper
Code

Leveraging the Feature Distribution in Transfer-based Few-Shot Learning

yhu01/PT-MAP • • 6 Jun 2020

Few-shot classification is a challenging problem due to the uncertainty caused by using few labelled samples.

6
Paper
Code

Towards a Neural Statistician

conormdurkan/neural-statistician • • 7 Jun 2016

We refer to our model as a neural statistician, and by this we mean a neural network that can learn to compute summary statistics of datasets without supervision.

5
Paper
Code

Few-Shot Learning via Embedding Adaptation with Set-to-Set Functions

Sha-Lab/FEAT • • CVPR 2020

Many few-shot learning methods address this challenge by learning an instance embedding function from seen classes and apply the function to instances from unseen classes with limited labels.

5
Paper
Code

DeepEMD: Differentiable Earth Mover's Distance for Few-Shot Learning

icoz69/DeepEMD • • 15 Mar 2020

We employ the Earth Mover's Distance (EMD) as a metric to compute a structural distance between dense image representations to determine image relevance.

5
Paper
Code

Low-shot Visual Recognition by Shrinking and Hallucinating Features

facebookresearch/low-shot-shrink-hallucinate • • ICCV 2017

Low-shot visual learning---the ability to recognize novel object categories from very few examples---is a hallmark of human visual intelligence.

4
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