Few-Shot Learning
1041 papers with code • 22 benchmarks • 41 datasets
Few-Shot Learning is an example of meta-learning, where a learner is trained on several related tasks, during the meta-training phase, so that it can generalize well to unseen (but related) tasks with just few examples, during the meta-testing phase. An effective approach to the Few-Shot Learning problem is to learn a common representation for various tasks and train task specific classifiers on top of this representation.
Source: Penalty Method for Inversion-Free Deep Bilevel Optimization
Benchmarks
These leaderboards are used to track progress in Few-Shot Learning
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
Libraries
Use these libraries to find Few-Shot Learning models and implementations
ImageNet
GLUE
SST
CUB-200-2011
UCF101
SST-2
Oxford 102 Flower
MRPC
DTD
Subtasks
Most implemented papers
Leveraging the Feature Distribution in Transfer-based Few-Shot Learning
yhu01/PT-MAP
•
•
Few-shot classification is a challenging problem due to the uncertainty caused by using few labelled samples.
Free Lunch for Few-shot Learning: Distribution Calibration
ShuoYang-1998/ICLR2021-Oral_Distribution_Calibration
•
•
ICLR 2021
In this paper, we calibrate the distribution of these few-sample classes by transferring statistics from the classes with sufficient examples, then an adequate number of examples can be sampled from the calibrated distribution to expand the inputs to the classifier.
Meta-learning with differentiable closed-form solvers
learnables/learn2learn
•
•
ICLR 2019
The main idea is to teach a deep network to use standard machine learning tools, such as ridge regression, as part of its own internal model, enabling it to quickly adapt to novel data.
Meta-Learning with Latent Embedding Optimization
We show that it is possible to bypass these limitations by learning a data-dependent latent generative representation of model parameters, and performing gradient-based meta-learning in this low-dimensional latent space.
Few-Shot Learning via Embedding Adaptation with Set-to-Set Functions
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.
DeepEMD: Differentiable Earth Mover's Distance for Few-Shot Learning
icoz69/DeepEMD
•
•
We employ the Earth Mover's Distance (EMD) as a metric to compute a structural distance between dense image representations to determine image relevance.
Calibrate Before Use: Improving Few-Shot Performance of Language Models
tonyzhaozh/few-shot-learning
•
•
We show that this type of few-shot learning can be unstable: the choice of prompt format, training examples, and even the order of the training examples can cause accuracy to vary from near chance to near state-of-the-art.
PaLM: Scaling Language Modeling with Pathways
lucidrains/CoCa-pytorch
•
•
Google Research 2022
To further our understanding of the impact of scale on few-shot learning, we trained a 540-billion parameter, densely activated, Transformer language model, which we call Pathways Language Model PaLM.
Flamingo: a Visual Language Model for Few-Shot Learning
mlfoundations/open_flamingo
•
•
DeepMind 2022
Building models that can be rapidly adapted to novel tasks using only a handful of annotated examples is an open challenge for multimodal machine learning research.
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).
