迁移学习笔记

---

Few-Shot Learning

code

• Github： Awesome-Few-Shot

papers

• [ICLR 2020] Cross-Domain Few-Shot Classification via Learned Feature-Wise Transformation [paper] [code]

• [ICCV 2019] Few-shot Object Detection via Feature Reweighting [paper] [code] [note]

• [ICCV 2019] Few-Shot Learning with Global Class Representations [paper] [code] [note]

• [ICCV 2019] Few-Shot Image Recognition with Knowledge Transfer [paper]

• [NIPS 2019] Meta-Reinforced Synthetic Data for One-Shot Fine-Grained Visual Recognition [paper] [code] [note]

• [CVPR 2019] Meta-Transfer Learning for Few-Shot Learning [paper] [code] [note] 使用深层网络进行小样本学习

• [CVPR 2019] IDeMe-Net: Image Deformation Meta-Networks for One-Shot Learning [paper] [code] [note]

• [ICML 2019] Learning What and Where to Transfer [paper] [code] [note]

• [CVPR 2018] Unsupervised Feature Learning via Non-Parametric Instance Discrimination [paper] [code] [note]

• [CVPR 2018] Learning to Compare: Relation Network for Few-Shot Learning [paper] [code]
  [note]

• [ICLR 2018] A Simple Neural Attentive Meta-Learner [paper]

• [ICLR 2017] Optimization as a Model for Few-Shot Learning [paper] [note]

• [PMLR 2017] MAML: Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks [paper] [code] [note]

• [NIPS 2017] Prototypical Networks for Few-shot Learning [paper] [code]

• [CVPR 2017] Multi-attention Network for One Shot Learning [paper]

• [NIPS 2016] Learning to learn by gradient descent by gradient descent [paper] [code] [note] Learn-to-Learn 用GD学习“用GD学习”

survey

• Small Sample Learning in Big Data Era [paper] [note]
• A Comprehensive Survey on Transfer Learning [paper] [blog]
• 小样本学习（Few-shot Learning）综述
  有错误：例子是5-way 1-shot，不是2-way 5-shot

report

1. 付彦伟-One-shot learning in semantic embedding and data augmentation
2. 何旭明-Learning Structured Visual Concepts with Few-shot Supervision

introduction

• ==⭐⭐⭐⭐⭐==Meta Learning 入门：MAML 和 Reptile

• IJCAI 19 罗杰波 few-shot_learning

• Few-shot learning 概览

• Few-shot learning 少样本学习

• 什么是小样本学习?

• 93篇few-shot learning的papers及其code链接

• 149篇meta-learning的papers

• 向人类幼儿学习小样本学习？

• 【机器之心】「分段映射」帮助利用少量样本习得新类别细粒度分类器

• 李宏毅机器学习2019 课程主页

• 李宏毅机器学习2019 元学习视频

• 李宏毅机器学习2019 元学习公式推导

• 从零开始，了解元学习

一些概念

• 标准误-SEM
  统计中标准误是用样本均值算一个标准差，小样本学习用采样任务的精度计算标准差。
  标准误1
  标准误2

• 95%置信区间-confidence interval
  95%置信水平，就是说做100次抽样，有95次的置信区间包含了总体均值。
  95%置信水平
  95%置信水平

---

Zero-Shot Learning

introduction

• What Is Zero-Shot Learning? [原文] [翻译]
• 零次学习（Zero-Shot Learning）入门
• 机器之心：零样本学习
• Zero-shot learning（一）：ZSL的基本概念
• Zero-shot learning（二）：ZSL关于嵌入模型的理解

code

• GitHub: awesome-zero-shot-learning

survey

• [ACM TIST 2019] A Survey of Zero-Shot Learning: Settings, Methods, and Applications [paper] [note]
  [自动化学报] 零样本学习研究进展

papers

• [TIP 2019] Zero-Shot Learning via Category-Specific Visual-Semantic Mapping and Label Refinement [paper]

• [TPAMI 2015] Transductive Multi-View Zero-Shot Learning [paper] TMV提出了域漂移问题

• [Neurocomputing 2019] Attribute Hierarchy based Multi-task Learning for Fine-grained Image Classification [paper]

• [IJAC 2019] Zero-Shot Fine-Grained Classification by Deep Feature Learning with Semantics [paper]

• [CVPR 2019] COSMO：Adaptive Confidence Smoothing for Generalized Zero-Shot Learning [paper]
  <==>DAZSL: Domain-Aware Generalized Zero-Shot Learning [arxiv]

• [CVPR 2019] Generative Dual Adversarial Network for Generalized Zero-shot Learning [paper] [note]

• [CVPR 2019] Gradient Matching Generative Networks for Zero-Shot Learning [paper]

• [CVPR 2019] f-VAEGAN-D2: A Feature Generating Framework for Any-Shot Learning [paper]

• [ICCV 2019] Transductive Learning for Zero-Shot Object Detection [paper]

• [NIPS 2019] Transductive Zero-Shot Learning with Visual Structure Constraint [paper] [code] [note]

• [NIPS 2019] Zero-shot Learning via Simultaneously Generating and Learning [paper]

• [CVPR 2018] Discriminative Learning of Latent Features for Zero-Shot Recognition [paper] [note] LDF提出学习隐含属性

• [CVPR 2018] Zero-Shot Visual Recognition Using Semantics-Preserving Adversarial Embedding Networks [paper] [note]

• [CVPR 2018] Generalized Zero-Shot Learning via Synthesized Examples [paper]

• [CVPR 2018] Generalized Zero-Shot Learning via Synthesized Examples [paper]

• [CVPR 2018] Feature Generating Networks for Zero-Shot Learning [paper]

• [CVPR 2018] Discriminative Learning of Latent Features for Zero-Shot Recognition [paper] [code] [note]

• [CVPR 2018] Transductive Unbiased Embedding for Zero-Shot Learning [paper] [note]

• [ECCV 2018] Multi-modal Cycle-consistent Generalized Zero-Shot Learning [paper]

• [ECCV 2018] Learning Class Prototypes via Structure Alignment for Zero-Shot Recognition [paper] [code] [note]

• [NIPS 2018] Stacked Semantics-Guided Attention Model for Fine-Grained Zero-Shot Learning [paper] [note] SGA提出注意力解决细粒度ZSL

• [IJCAI 2018] Incomplete Multi-ViewWeak-Label Learning [paper]

• [ICCV 2017] Label Efficient Learning of TransferableRepresentations across Domains and Tasks [paper]

• [ICCV 2017] Attributes2Classname: A Discriminative Model for Attribute-Based Unsupervised Zero-Shot Learning [paper] [code]

• [ICCV 2017] Predicting Visual Exemplars of Unseen Classes for Zero-Shot Learning [paper]

• [ICCV 2017] Learning Discriminative Latent Attributes for Zero-Shot Classification [paper] [code] [note]

• [CVPR 2017] Matrix Tri-Factorization with Manifold Regularization for Zero-shot Learning [paper] [note]

• [CVPR 2015] Evaluation of Output Embeddings for Fine-Grained Image Classification [paper]

• [CVPR 2016] Learning Learning Deep Representations of Fine-Grained Visual Descriptions [paper]

---

Class Incremental Learning

survey

• [CAPE 2017] A Survey on Incremental Learning [paper] [note]

paper

• [arxiv 2020] Few-Shot Class-Incremental Learning via Feature Space Composition [paper]
• [TPAMI 2020] Novelty Detection and Online Learning for Chunk Data Streams [paper]
• [IJCAI 2018] Fast Factorization-Free Kernel Learning for Unlabeled Chunk Data Streams [paper] [note]
• [NIPS 2018] delta encoder an effective sample synthesis method for few shot object recognition [paper] [note]
• [AAAI 2017] Fast Online Incremental Learning on Mixture Streaming Data [paper]
• [CVPR 2017] Incremental Kernel Null Space Discriminant Analysis for Novelty Detection [paper]
• [CVPR 2013] Kernel Null Space Methods for Novelty Dection [paper]
• [TNNLS 2015] Incremeantal Linear Discriminant Analysis: A Fast Algorithm and Comparisons [paper]
• [NIPS 2000] Incremental and Decremental Support Vector Machine Learning [paper]

---

Transfer Learning

• [NIPS 2018] GLoMo Unsupervisedly Learned Relational Graphs as Transferable Representations [paper] [note]
• [CVPR 2018 best] Taskonomy: Disentangling Task Transfer Learning [paper] [blog of author] [note] [Analytic Hierarchy Process]

Domain Adaptation

• [ECCV 2018] Domain Adaptation for Semantic Segmentation via Class-Balanced Self-Training [paper] [code]

• [ECCV 2018] Two at Once: Enhancing Learning and Generalization Capacities via IBN-Net [paper] [code] [note]

• [ICCV 2019] Episodic Training for Domain Generalization [paper]