There are some papers/articles need to read.
- Meta learning
- Metric learning
- Few-shot learning
- One-shot learning
- Zero-shot learning
- GAN
- VAE
These are the methods based on metric distance for few-shot learning.
- Siamese Neural Networks for One-Shot Image Recognition
- FaceNet: A Unified Embedding for Face Recognition and Clustering
- Deep Metric Learning Using Triplet Network
Some papers from Google DeepMind, should read in the order.
- Neural Turing Machines
- One-shot Learning with Memory-Augmented Neural Networks
- Matching Networks for One Shot Learning
- Feature Generating Networks for Zero-ShsoetenLearning
- Large Margin Few-Shot Learning
- Label-Embedding for Image Classification
- Evaluation of Output Embeddings for Fine-Grained Image Classification
- Learning Deep Representations of Fine-Grained Visual Descriptions
- Transductive Unbiased Embedding for Zero-Shot Learning
- Related articles: From Zero to Hero: Shaking Up the Field of Zero-shot Learning
- Recent Advances in Zero-shot Recognition
- An embarrassingly simple approach to zero-shot learning
These are the methods based on meta learning for few-shot learning.
The most popular two are MAML and Reptile.
- On First-Order Meta-Learning Algorithms
- Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
- META-LEARNING FOR SEMI-SUPERVISED FEW-SHOT CLASSIFICATION
- Meta-Learning with Latent Embedding Optimization
This is the overview of learning to learn written by berkeley AI research.
This article introduced the meta-learning by animation clearly, one of the best explaination of meta-learning I think.
This article explain the Reptile, which is from the paper: On First-Order Meta-Learning Algorithms.
It's a new paper from NIPS 2018, by IBM research AI.
- ∆-encoder: an effective sample synthesis method for few-shot object recognition
- MetaGAN: An Adversarial Approach to Few-Shot Learning
- It's better to read the paper about MAML, Relation Network, DAGAN before.
- Data Agumentation Generative Adversarial Networks