One-Shot Learning

69 papers with code • 1 benchmarks • 3 datasets

One-shot learning is the task of learning information about object categories from a single training example.

( Image credit: Siamese Neural Networks for One-shot Image Recognition )

Libraries

Use these libraries to find One-Shot Learning models and implementations

Most implemented papers

Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks

cbfinn/maml ICML 2017

We propose an algorithm for meta-learning that is model-agnostic, in the sense that it is compatible with any model trained with gradient descent and applicable to a variety of different learning problems, including classification, regression, and reinforcement learning.

Prototypical Networks for Few-shot Learning

oscarknagg/few-shot NeurIPS 2017

We propose prototypical networks for the problem of few-shot classification, where a classifier must generalize to new classes not seen in the training set, given only a small number of examples of each new class.

Matching Networks for One Shot Learning

oscarknagg/few-shot NeurIPS 2016

Our algorithm improves one-shot accuracy on ImageNet from 87. 6% to 93. 2% and from 88. 0% to 93. 8% on Omniglot compared to competing approaches.

One-shot Learning with Memory-Augmented Neural Networks

tristandeleu/ntm-one-shot 19 May 2016

Despite recent breakthroughs in the applications of deep neural networks, one setting that presents a persistent challenge is that of "one-shot learning."

Siamese neural networks for one-shot image recognition

tensorfreitas/Siamese-Networks-for-One-Shot-Learning ICML deep learning workshop, vol. 2. 2015. 2015

The process of learning good features for machine learning applications can be very computationally expensive and may prove difficult in cases where little data is available.

The Omniglot challenge: a 3-year progress report

brendenlake/omniglot 9 Feb 2019

Three years ago, we released the Omniglot dataset for one-shot learning, along with five challenge tasks and a computational model that addresses these tasks.

Few-Shot Adversarial Learning of Realistic Neural Talking Head Models

vincent-thevenin/Realistic-Neural-Talking-Head-Models ICCV 2019

In order to create a personalized talking head model, these works require training on a large dataset of images of a single person.

One-Shot Learning for Semantic Segmentation

lzzcd001/OSLSM 11 Sep 2017

Low-shot learning methods for image classification support learning from sparse data.

Dynamic Few-Shot Visual Learning without Forgetting

gidariss/FewShotWithoutForgetting CVPR 2018

In this context, the goal of our work is to devise a few-shot visual learning system that during test time it will be able to efficiently learn novel categories from only a few training data while at the same time it will not forget the initial categories on which it was trained (here called base categories).

'Less Than One'-Shot Learning: Learning N Classes From M<N Samples

ilia10000/SLkNN 17 Sep 2020

We propose the `less than one'-shot learning task where models must learn $N$ new classes given only $M<N$ examples and we show that this is achievable with the help of soft labels.