few-shot learning ---综述

小样本学习（Few-shot Learning）综述 （出自阿里巴巴团队2019年4月）

Few-shot Learning: A Survey YAQING WANG1,2 , QUANMING YAO 2019

IBM-小样本学习（Few-shot Learning）State of the art 方法及论文讲解

CVPR 2019提前看：少样本学习专题

数据增广

模型

多任务学习

多任务学习用于few-shot的办法是：将其它数据集上训练好的参数，共享给小数据集。
Hard Parameter Sharing. This strategy explicitly shares parameter among tasks , and can additionally learn a task-specific parameter for each task to account for task specialties.
In [ Fine-grained visual categorization using meta-learning optimization with sample selection of auxiliary data], this is done by sharing the first several layers of two networks to learn the generic information, while learning a different last layer to deal with different output for each task

附录：相关论文及代码
[NIPS 2018 论文笔记] Stacked Semantics-Guided Attention Model for Fine-Grained Zero-Shot Learning
论文地址 代码地址

NIPS 2018：Zero-Shot Transfer with Deictic Object-Oriented Representation in Reinforcement Learning
NIPS 2018：Uncertainty-Aware Few-Shot Learning with Probabilistic Model-Agnostic Meta-Learning
NIPS 2018：Multitask Reinforcement Learning for Zero-shot Generalization with Subtask Dependencies
NIPS 2018：Stacked Semantics-Guided Attention Model for Fine-Grained Zero-Shot Learning
NIPS 2018：Delta-encoder: an effective sample synthesis method for few-shot object recognition
NIPS 2018：MetaGAN: An Adversarial Approach to Few-Shot Learning
NIPS 2018：One-Shot Unsupervised Cross Domain Translation
NIPS 2018：Generalized Zero-Shot Learning with Deep Calibration Network
NIPS 2018：Low-shot Learning via Covariance-Preserving Adversarial Augmentation Network
NIPS 2018：Improved few-shot learning with task conditioning and metric scaling
NIPS 2018：Adapted Deep Embeddings: A Synthesis of Methods for k-Shot Inductive Transfer Learning

ECCV2018：Y. Zhang, H. Tang, and K. Jia. 2018. Fine-grained visual categorization using meta-learning optimization with sample selection of auxiliary data.