迁移学习荟萃20191209

综述

• 领域综述
  • 2019 A Comprehensive Survey on Transfer Learning
  • 2019 Transfer Adaptation Learning: A Decade Survey
  • 2018 Transfer Metric Learning: Algorithms, Applications and Outlooks
  • 2018 Asymmetric Heterogeneous Transfer Learning: A Survey
  • 2018 Neural Style Transfer: A Review
  • 2018 Deep Visual Domain Adaptation: A Survey
  • 2017 A survey on multi-task learning
  • 2017 A survey on heterogeneous transfer learning
  • 2017 Cross-dataset recognition: a survey
  • 2016 A survey of transfer learning
  • 2015 迁移学习研究进展
  • 2009 A survey on transfer learning
• 迁移学习应用综述
  • Visual Domain Adaptation: A Survey of Recent Advances
  • Transfer Learning for Activity Recognition: A Survey
  • Transfer Learning for Reinforcement Learning Domains: A Survey
  • A Survey of Multi-source Domain Adaptation
  • 2019 A Survey of Sentiment Analysis Based on Transfer Learning

理论

• 20191008 CVPR-19 Characterizing and Avoiding Negative Transfer
• 20190301 ALT-19 A Generalized Neyman-Pearson Criterion for Optimal Domain Adaptation
• 20181219 arXiv PAC Learning Guarantees Under Covariate Shift
• 20181206 arXiv Transferring Knowledge across Learning Processes
• 20181128 arXiv Theoretical Guarantees of Transfer Learning
• 20181117 arXiv Theoretical Perspective of Deep Domain Adaptation
• 20181106 workshop GENERALIZATION BOUNDS FOR DOMAIN ADAPTATION VIA DOMAIN TRANSFORMATIONS
• 20191202 AAAI-20 Towards Oracle Knowledge Distillation with Neural Architecture Search
• 20191202 AAAI-20 Stable Learning via Sample Reweighting
• 20191202 arXiv Domain-invariant Stereo Matching Networks
• 20191202 arXiv Learning Generalizable Representations via Diverse Supervision
• 20191202 arXiv Domain-Aware Dynamic Networks
• 20191029 Adversarial Feature Alignment: Avoid Catastrophic Forgetting in Incremental Task Lifelong Learning
• 20191029 Reducing Domain Gap via Style-Agnostic Networks
• 20191015 arXiv The Visual Task Adaptation Benchmark
• 20191011 arXiv Estimating Transfer Entropy via Copula Entropy
• 20191011 arXiv Learning to Remember from a Multi-Task Teacher
• 20191008 arXiv DIVA: Domain Invariant Variational Autoencoders
• 20190821 arXiv Transfer Learning-Based Label Proportions Method with Data of Uncertainty
• 20190806 KDD-19 Relation Extraction via Domain-aware Transfer Learning
• 20190703 arXiv Inferred successor maps for better transfer learning
• 20190626 arXiv Transfer of Machine Learning Fairness across Domains
• 20190531 IJCAI-19 Adversarial Imitation Learning from Incomplete Demonstrations
• 20190517 arXiv Budget-Aware Adapters for Multi-Domain Learning
• 20190409 arXiv Improving Image Classification Robustness through Selective CNN-Filters Fine-Tuning
• 20190401 arXiv Distilling Task-Specific Knowledge from BERT into Simple Neural Networks
• 20190305 arXiv Let’s Transfer Transformations of Shared Semantic Representations
• 20190301 SysML-19 FixyNN: Efficient Hardware for Mobile Computer Vision via Transfer Learning
• 20190118 arXiv Domain Adaptation for Structured Output via Discriminative Patch Representations
• 20190111 arXiv Low-Cost Transfer Learning of Face Tasks
• 20190111 arXiv Transfer Representation Learning with TSK Fuzzy System
• 20190102 arXiv An introduction to domain adaptation and transfer learning
• 20181217 arXiv When Semi-Supervised Learning Meets Transfer Learning: Training Strategies, Models and Datasets
• 20181127 arXiv Privacy-preserving Transfer Learning for Knowledge Sharing
• 20181121 arXiv An Efficient Transfer Learning Technique by Using Final Fully-Connected Layer Output Features of Deep Networks
• 20181121 arXiv Not just a matter of semantics: the relationship between visual similarity and semantic similarity
• 20181008 arXiv Unsupervised Learning via Meta-Learning
• 20101008 arXiv Concept-drifting Data Streams are Time Series; The Case for Continuous Adaptation
• 20180925 arXiv DT-LET: Deep Transfer Learning by Exploring where to Transfer
• 20180919 JMLR Invariant Models for Causal Transfer Learning
• 20180912 arXiv Transfer Learning with Neural AutoML
• 20190904 arXiv On the Minimal Supervision for Training Any Binary Classifier from Only Unlabeled Data
• 20180904 arXiv Learning Data-adaptive Nonparametric Kernels
• 20180901 arXiv Distance Based Source Domain Selection for Sentiment Classification
• 20180901 KBS Transfer subspace learning via low-rank and discriminative reconstruction matrix
• 20180825 arXiv Transfer Learning for Estimating Causal Effects using Neural Networks
• 20180724 ICPKR-18 Knowledge-based Transfer Learning Explanation
• 20180628 arXiv：Syn2Real: A New Benchmark forSynthetic-to-Real Visual Domain Adaptation
• 20180605 arXiv：Federated Learning with Non-IID Data
• 20180604 arXiv：Learning Factorized Representations for Open-set Domain Adaptation
• 20180403 arXiv：Class Subset Selection for Transfer Learning using Submodularity
• 20180326 ICMLA-17：Comparing Transfer Learning and Traditional Learning Under Domain Class Imbalance

模型算法

多源迁移学习

• 20190902 AAAI-19 Aligning Domain-Specific Distribution and Classifier for Cross-Domain Classification from Multiple Sources
• 20181212 AIKP Multi-source Transfer Learning
• 20181207 arXiv Moment Matching for Multi-Source Domain Adaptation
• CoRR abs/1711.09020 (2017) StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translation
• 20180524 arXiv：Algorithms and Theory for Multiple-Source Adaptation
• 20181117 AAAI-19 Robust Optimization over Multiple Domains
• 20180912 arXiv Multi-target Unsupervised Domain Adaptation without Exactly Shared Categories
• 20180316 arXiv Optimal Transport for Multi-source Domain Adaptation under Target Shift

异构迁移学习

• 20190717 AAAI Heterogeneous Transfer Learning via Deep Matrix Completion with Adversarial Kernel Embedding
• 20190829 ACMMM-19 Heterogeneous Domain Adaptation via Soft Transfer Network
• 20181113 ACML-18 Unsupervised Heterogeneous Domain Adaptation with Sparse Feature Transformation
• 20180901 TKDE A General Domain Specific Feature Transfer Framework for Hybrid Domain Adaptation
• 20180606 arXiv：Asymmetric Heterogeneous Transfer Learning: A Survey
• 20180403 Neural Processing Letters-18：Label Space Embedding of Manifold Alignment for Domain Adaption
• 20180105 arXiv: Heterogeneous transfer learning

在线迁移学习

• 20180326 Online domain adaptation by exploiting labeled features and pro-active learning
• 20180128 ICML-10上 Online Transfer Learning
• 20180126 Online transfer learning by leveraging multiple source domains
• 20180126 Online Heterogeneous Transfer by Hedge Ensemble of Offline and Online Decisions
• 20180126 TKDE-17：Online Transfer Learning with Multiple Homogeneous or Heterogeneous Sources
• KIS-17 Online transfer learning by leveraging multiple source domains
• CIKM-13 OMS-TL: A Framework of Online Multiple Source Transfer Learning
• ICLR-17 ONLINE BAYESIAN TRANSFER LEARNING FOR SEQUENTIAL DATA MODELING
• KDD-14 Scalable Hands-Free Transfer Learning for Online Advertising
• TNNLS-17 Online Feature Transformation Learning for Cross-Domain Object Category Recognition
• ICPR-12 Online Transfer Boosting for Object Tracking
• TKDE-14 Online Feature Selection and Its Applications
• AAAI-15 Online Transfer Learning in Reinforcement Learning Domains
• AAAI-15 Online Boosting Algorithms for Anytime Transfer and Multitask Learning
• IJSR-13 Knowledge Transfer Using Cost Sensitive Online Learning Classification

小样本学习

• 20190813 arXiv Domain-Specific Embedding Network for Zero-Shot Recognition
• 20190401 TIp-19 Few-Shot Deep Adversarial Learning for Video-based Person Re-identification
• 20190305 arXiv Zero-Shot Task Transfer
• 20190221 arXiv Adaptive Cross-Modal Few-Shot Learning
• 20180612 CVPR-18 泛化的Zero-shot learning：Generalized Zero-Shot Learning via Synthesized Examples
• 20181106 arXiv Zero-Shot Transfer VQA Dataset
• 20171222 NIPS 2017：Few-Shot Adversarial Domain Adaptation
• 20181225 arXiv Learning Compositional Representations for Few-Shot Recognition
  • Few-shot recognition
• 20181127 WACV-19 Self Paced Adversarial Training for Multimodal Few-shot Learning
• 20180728 arXiv Meta-learning autoencoders for few-shot prediction
• 20171216 arXiv Zero-Shot Deep Domain Adaptation
• 20190409 ICLR-19 A Closer Look at Few-shot Classification
• 20190401 IJCNN-19 Zero-shot Image Recognition Using Relational Matching, Adaptation and Calibration
• 20190301 NeurIPS-18 workshp One-Shot Federated Learning
  • One-shot federated learning
• 20171022 ICCVW-17 Zero-shot learning posed as a missing data problem
• 20180516 arXiv-18 A Large-scale Attribute Dataset for Zero-shot Learning
• 20180710 ICML-18 MSplit LBI: Realizing Feature Selection and Dense Estimation Simultaneously in Few-shot and Zero-shot Learning
• 20190108 WACV-19 Zero-shot Learning via Recurrent Knowledge Transfer

深度迁移学习

• 非对抗深度迁移
  • 20191201 arXiv A Unified Framework for Lifelong Learning in Deep Neural Networks
  • 20191201 arXiv ReMixMatch: Semi-Supervised Learning with Distribution Alignment and Augmentation Anchoring
  • 20191119 ICDM-19 Towards Making Deep Transfer Learning Never Hurt
  • 20191119 NIPS-19 workshop Collaborative Unsupervised Domain Adaptation for Medical Image Diagnosis
  • 20191119 NIPS-19 Transferable Normalization: Towards Improving Transferability of Deep Neural Networks
  • 20191029 KBS Semi-supervised representation learning via dual autoencoders for domain adaptation
  • 20190929 NeurIPS-19 Deep Model Transferability from Attribution Maps
  • 20190926 arXiv Learning a Domain-Invariant Embedding for Unsupervised Domain Adaptation Using Class-Conditioned Distribution Alignment
  • 20190926 arXiv A Deep Learning-Based Approach for Measuring the Domain Similarity of Persian Texts
  • 20190926 arXiv Transfer Learning across Languages from Someone Else’s NMT Model
  • 20190926 arXiv FEED: Feature-level Ensemble for Knowledge Distillation
  • 20190926 ICCV-19 Self-similarity Grouping: A Simple Unsupervised Cross Domain Adaptation Approach for Person Re-identification
  • 20190910 BMVC-19 Curriculum based Dropout Discriminator for Domain Adaptation
  • 20190909 IJCAI-FML-19 FedHealth: A Federated Transfer Learning Framework for Wearable Healthcare
  • 20190909 PAMI Inferring Latent Domains for Unsupervised Deep Domain Adaptation
  • 20190729 ICCV workshop Multi-level Domain Adaptive learning for Cross-Domain Detection
  • 20190626 IJCAI-19 Bayesian Uncertainty Matching for Unsupervised Domain Adaptation
  • 20190419 CVPR-19 DDLSTM: Dual-Domain LSTM for Cross-Dataset Action Recognition
  • 20190109 InfSc Robust Unsupervised Domain Adaptation for Neural Networks via Moment Alignment
  • 20181212 ICONIP-18 Domain Adaptation via Identical Distribution Across Models and Tasks
  • 20181212 AIKP Deep Domain Adaptation
  • 20181211 arXiv Deep Variational Transfer: Transfer Learning through Semi-supervised Deep Generative Models
  • 20181207 arXiv Feature Matters: A Stage-by-Stage Approach for Knowledge Transfer
  • 20181128 arXiv Low-resolution Face Recognition in the Wild via Selective Knowledge Distillation
  • 20181128 arXiv One Shot Domain Adaptation for Person Re-Identification
  • 20181123 arXiv SpotTune: Transfer Learning through Adaptive Fine-tuning
  • 20181121 arXiv Integrating domain knowledge: using hierarchies to improve deep classifiers
  • 20181117 arXiv AdapterNet - learning input transformation for domain adaptation
  • 20181115 AAAI-19 Exploiting Local Feature Patterns for Unsupervised Domain Adaptation
  • 20181115 NIPS-18 Co-regularized Alignment for Unsupervised Domain Adaptation
  • 20181113 NIPS-18 Generalized Zero-Shot Learning with Deep Calibration Network
  • 20181110 AAAI-19 Knowledge Transfer via Distillation of Activation Boundaries Formed by Hidden Neurons
  • 20181109 PAMI-18 Transferable Representation Learning with Deep Adaptation Networks
  • 20181108 arXiv Deep feature transfer between localization and segmentation tasks
  • 20181107 BigData-18 Transfer learning for time series classification
  • 20181106 PRCV-18 Deep Local Descriptors with Domain Adaptation
  • 20181106 LNCS-18 LSTN: Latent Subspace Transfer Network for Unsupervised Domain Adaptation
  • 20181105 SIGGRAPI-18 Unsupervised representation learning using convolutional and stacked auto-encoders: a domain and cross-domain feature space analysis
  • 20181105 arXiv Progressive Memory Banks for Incremental Domain Adaptation
  • 20180909 arXiv A Survey on Deep Transfer Learning
  • 20180901 arXiv Joint Domain Alignment and Discriminative Feature Learning for Unsupervised Deep Domain Adaptation
  • 20180819 arXiv Conceptual Domain Adaptation Using Deep Learning
  • 20180731 ECCV-18 DeepJDOT: Deep Joint Distribution Optimal Transport for Unsupervised Domain Adaptation
  • 20180731 ICLR-18 Few Shot Learning with Simplex
  • 20180724 AIAI-18 Improving Deep Models of Person Re-identification for Cross-Dataset Usage
  • 20180724 ECCV-18 Zero-Shot Deep Domain Adaptation
  • 20180724 ICCSE-18 Deep Transfer Learning for Cross-domain Activity Recognition
  • 20180530 arXiv domain adaptation方法：Robust Unsupervised Domain Adaptation for Neural Networks via Moment Alignment
  • 20180522 arXiv ：Cross-domain attribute representation based on convolutional neural network
  • 20180428 CVPR-18：Deep Mutual Learning
  • 20180428 ICLR-18：Self-ensembling for visual domain adaptation
  • 20180428 IJCAI-18：Better and Faster: Knowledge Transfer from Multiple Self-supervised Learning Tasks via Graph Distillation for Video Classification
  • 20180426 arXiv ：Parameter Transfer Unit for Deep Neural Networks
  • 20180425 CVPR-18(oral) ：Taskonomy: Disentangling Task Transfer Learning
  • 20180410 ICLR-17 ：Variational Recurrent Adversarial Deep Domain Adaptation
  • 20180403 arXiv ：Hierarchical Transfer Convolutional Neural Networks for Image Classification
  • 20180402 CVPR-18 ：Cross-Domain Weakly-Supervised Object Detection through Progressive Domain Adaptation
  • 20180329 arXiv ：End-to-End Multi-Task Learning with Attention
  • 20180326 arXiv ：Domain Adaptive Faster R-CNN for Object Detection in the Wild
  • 20180326 Pattern Recognition-17 ：Multi-label Learning Based Deep Transfer Neural Network for Facial Attribute Classification
  • 20180326 ：Layer-wise domain correction for unsupervised domain adaptation
  • 20180326 Pattern Recognition-17 ：Adaptive Batch Normalization for practical domain adaptation
  • 20180309 arXiv ：Transfer Automatic Machine Learning
  • 2018 ICLR-18 Minimal-Entropy Correlation Alignment for Unsupervised Deep Domain Adaptation code
  • 2018 arXiv ：Deep Visual Domain Adaptation: A Survey
  • ICLR-17 Central Moment Discrepancy (CMD) for Domain-Invariant Representation Learning
  • ICCV-17 AutoDIAL: Automatic DomaIn Alignment Layers
  • ICCV-17 CCSA: Unified Deep Supervised Domain Adaptation and Generalization
  • ICML-17 JAN: Deep Transfer Learning with Joint Adaptation Networks
  • 2017 Google: Learning Transferable Architectures for Scalable Image Recognition
  • NIPS-16 RTN: Unsupervised Domain Adaptation with Residual Transfer Networks
  • CoRR abs/1603.04779 (2016) AdaBN: Revisiting batch normalization for practical domain adaptation
  • JMLR-16 DANN: Domain-adversarial training of neural networks
  • 20171226 NIPS 2016 ：Domain Separation Networks
  • 20171222 ICCV 2017 ：Unified Deep Supervised Domain Adaptation and Generalization
  • 20171126 NIPS-17 Label Efficient Learning of Transferable Representations acrosss Domains and Tasks
  • 201711：基于深度学习和迁移学习的识花实践
  • ECCV-16 Deep CORAL: Correlation Alignment for Deep Domain Adaptation
  • ECCV-16 DRCN: Deep Reconstruction-Classification Networks for Unsupervised Domain Adaptation
  • ICML-15 DAN: Learning Transferable Features with Deep Adaptation Networks
  • ICML-15 GRL: Unsupervised Domain Adaptation by Backpropagation
  • ICCV-15 Simultaneous Deep Transfer Across Domains and Tasks
  • NIPS-14 How transferable are features in deep neural networks?
  • CoRR abs/1412.3474 (2014) Deep Domain Confusion(DDC): Maximizing for Domain Invariance
  • ICML-14 ：DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition
  • Simultaneous Deep Transfer Across Domains and Tasks
  • 深度适配网络（Deep Adaptation Network, DAN）
  • 深度联合适配网络（Joint Adaptation Network, JAN）
• 对抗迁移学习
  • 20190916 arXiv Compound Domain Adaptation in an Open World
  • 20101008 ICCV-19 Enhancing Adversarial Example Transferability with an Intermediate Level Attack
  • 20190531 arXiv Adaptive Deep Kernel Learning
  • 20190531 arXiv Multi-task Learning in Deep Gaussian Processes with Multi-kernel Layers
  • 20190531 arXiv Image Alignment in Unseen Domains via Domain Deep Generalization
  • 20190408 arXiv DeceptionNet: Network-Driven Domain Randomization
  • 20190220 arXiv Fully-Featured Attribute Transfer
  • 20190220 arXiv Unsupervised Domain Adaptation using Deep Networks with Cross-Grafted Stacks
  • 20181217 arXiv DLOW: Domain Flow for Adaptation and Generalization
  • 20181212 arXiv Learning Transferable Adversarial Examples via Ghost Networks
  • 20181211 arXiv Adversarial Transfer Learning
  • 20181205 arXiv Unsupervised Domain Adaptation using Generative Models and Self-ensembling
  • 20181205 arXiv VADRA: Visual Adversarial Domain Randomization and Augmentation
  • 20181130 arXiv Identity Preserving Generative Adversarial Network for Cross-Domain Person Re-identification
  • 20181129 AAAI-19 Exploiting Coarse-to-Fine Task Transfer for Aspect-level Sentiment Classification
  • 20181128 arXiv Geometry-Consistent Generative Adversarial Networks for One-Sided Unsupervised Domain Mapping
  • 20181127 arXiv Distorting Neural Representations to Generate Highly Transferable Adversarial Examples
  • 20181123 arXiv Progressive Feature Alignment for Unsupervised Domain Adaptation - Progressively selecting confident pseudo labeled samples for transfer
  • 20181113 NIPS-18 Conditional Adversarial Domain Adaptation
  • 20181107 NIPS-18 Invariant Representations without Adversarial Training
  • 20181105 arXiv Efficient Multi-Domain Dictionary Learning with GANs
  • 20181012 arXiv Domain Confusion with Self Ensembling for Unsupervised Adaptation
  • 20180912 arXiv Improving Adversarial Discriminative Domain Adaptation
  • 20180731 ECCV-18 Dist-GAN: An Improved GAN using Distance Constraints
  • 20180724 arXiv Generalization Bounds for Unsupervised Cross-Domain Mapping with WGANs
  • 20180724 ECCV-18 Unsupervised Image-to-Image Translation with Stacked Cycle-Consistent Adversarial Networks
  • 20180628 ICML-18：CyCADA: Cycle-Consistent Adversarial Domain Adaptation
  • 20180619 CVPR-18：Re-weighted Adversarial Adaptation Network for Unsupervised Domain Adaptation
  • 20180616 CVPR-18：Generate To Adapt: Aligning Domains using Generative Adversarial Networks
  • 20180612 ICML-18：RadialGAN: Leveraging multiple datasets to improve target-specific predictive models using Generative Adversarial Networks
  • 20180612 ICML-18：JointGAN: Multi-Domain Joint Distribution Learning with Generative Adversarial Nets
  • 20180605 arXiv NAM: Non-Adversarial Unsupervised Domain Mapping
  • 20180508 arXiv：Transferring GANs: generating images from limited data
  • 20180501 arXiv：Open Set Domain Adaptation by Backpropagation
  • 20180427 arXiv：Unsupervised Domain Adaptation with Adversarial Residual Transform Networks
  • 20180424 CVPR-18：Adversarial Feature Augmentation for Unsupervised Domain Adaptation
  • 20180413 arXiv：Simple Domain Adaptation with Class Prediction Uncertainty Alignment
  • 20180413 arXiv：Causal Generative Domain Adaptation Networks
  • 20180410 CVPR-18(oral) ：Maximum Classifier Discrepancy for Unsupervised Domain Adaptation 代码
  • 20180403 CVPR-18：Importance Weighted Adversarial Nets for Partial Domain Adaptation
  • 20180326 MLSP-17：Adversarial domain separation and adaptation
  • 20180326 ICIP-17：Semi-supervised domain adaptation via convolutional neural network
  • 20180226 CVPR-18 Partial Transfer Learning with Selective Adversarial Networks
  • 20180116 ICLR-18 Stable Distribution Alignment using the Dual of the Adversarial Distance
  • 20180111 arXiv Stable Distribution Alignment Using the Dual of the Adversarial Distance
  • 20180110 AAAI-18 Wasserstein Distance Guided Representation Learning for Domain Adaptation
  • 20171218 arXiv Partial Transfer Learning with Selective Adversarial Networks
  • 201707 CVPR-17：Adversarial Representation Learning For Domain Adaptation
  • AAAI-18 Multi-Adversarial Domain Adaptation
  • ICCV-17 CycleGAN: Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks
  • ICCV-17 DualGAN: DualGAN: Unsupervised Dual Learning for Image-to-Image Translation
  • CVPR-17 Asymmetric Tri-training for Unsupervised Domain Adaptation
  • ICML-17 DiscoGAN: Learning to Discover Cross-Domain Relations with Generative Adversarial Networks

多任务学习

• 20191202 arXiv AdaShare: Learning What To Share For Efficient Deep Multi-Task Learning
• 20191125 AAAI-20 Adaptive Activation Network and Functional Regularization for Efficient and Flexible Deep Multi-Task Learning
• 20191015 arXiv Gumbel-Matrix Routing for Flexible Multi-task Learning
• 20190718 arXiv Task Selection Policies for Multitask Learning
• 20190509 FG-19 Multi-task human analysis in still images: 2D/3D pose, depth map, and multi-part segmentation
• 20190409 NAACL-19 AutoSeM: Automatic Task Selection and Mixing in Multi-Task Learning
• 20190409 TNNLS-19 Heterogeneous Multi-task Metric Learning across Multiple Domains
• 20190409 NeurIPS-18 Synthesized Policies for Transfer and Adaptation across Tasks and Environments
• 20190408 ICMR-19 Learning Task Relatedness in Multi-Task Learning for Images in Context
• 20190408 CVPR-19 End-to-End Multi-Task Learning with Attention
• 20190401 arXiv Many Task Learning with Task Routing
• 20190324 arXiv A Principled Approach for Learning Task Similarity in Multitask Learning
• 20181128 arXiv A Framework of Transfer Learning in Object Detection for Embedded Systems
• 20181012 NIPS-18 Multi-Task Learning as Multi-Objective Optimization
• 20181008 PSB-19 The Effectiveness of Multitask Learning for Phenotyping with Electronic Health Records Data
• 20180828 arXiv Self-Paced Multi-Task Clustering
• 20180622 arXiv：Uncertainty in Multitask Transfer Learning
• 20180524 arXiv：Learning to Multitask

强化迁移学习

• 20190821 arXiv Transfer in Deep Reinforcement Learning using Knowledge Graphs
• 20190320 arXiv Learning to Augment Synthetic Images for Sim2Real Policy Transfer
• 20190305 arXiv [Sim-to-Real Transfer for Biped Locomotion]
• 20190220 arXiv DIViS: Domain Invariant Visual Servoing for Collision-Free Goal Reaching
• 20181212 NeurIPS-18 workshop Efficient transfer learning and online adaptation with latent variable models for continuous control
• 20181128 arXiv Hardware Conditioned Policies for Multi-Robot Transfer Learning
• 20180926 arXiv Target Transfer Q-Learning and Its Convergence Analysis
• 20180926 arXiv Domain Adaptation in Robot Fault Diagnostic Systems
• 20180912 arXiv VPE: Variational Policy Embedding for Transfer Reinforcement Learning
• 20180909 arXiv Transferring Deep Reinforcement Learning with Adversarial Objective and Augmentation
• 20180530 ICML-18 ：Importance Weighted Transfer of Samples in Reinforcement Learning
• 20180524 arXiv：Learning Sampling Policies for Domain Adaptation
• 20180516 arXiv：Adversarial Task Transfer from Preference
• 20180413 NIPS-17：Successor Features for Transfer in Reinforcement Learning
• 20180404 IEEE TETCI-18：StarCraft Micromanagement with Reinforcement Learning and Curriculum Transfer Learning

迁移度量学习

• 20190515 TNNLS-19 A Distributed Approach towards Discriminative Distance Metric Learning
• 20190409 TNNLS-19 Heterogeneous Multi-task Metric Learning across Multiple Domains
• 20190409 PAMI-19 Transferring Knowledge Fragments for Learning Distance Metric from A Heterogeneous Domain
• 20190409 arXiv Decomposition-Based Transfer Distance Metric Learning for Image Classification
• 20181012 arXiv Transfer Metric Learning: Algorithms, Applications and Outlooks
• 20180622 arXiv：DEFRAG: Deep Euclidean Feature Representations through Adaptation on the Grassmann Manifold
• 20181117 arXiv Distance Measure Machines
• 20180605 KDD-10：Transfer metric learning by learning task relationships
• 20180606 arXiv：A Unified Framework for Domain Adaptation using Metric Learning on Manifolds
• 20180605 CVPR-15：Deep metric transfer learning
• 20180425 arXiv：CactusNets: Layer Applicability as a Metric for Transfer Learning

终身迁移学习

• 20190912 NeurIPS-19 Meta-Learning with Implicit Gradients
• 20180323 arXiv ：Incremental Learning-to-Learn with Statistical Guarantees
• 20180111 arXiv Lifelong Learning for Sentiment Classification

相关资源

• https://github.com/jindongwang/transferlearning
• https://github.com/artix41/awesome-transfer-learning
• https://paperswithcode.com/task/transfer-learning

领域专家

• Qiang Yang @ HKUST

  http://www.cs.ust.hk/~qyang/

• Lixin Duan @ UESTC

  http://www.lxduan.info/

• Mingsheng Long @ THU

  http://ise.thss.tsinghua.edu.cn/~mlong/

• Judy Hoffman @ UC Berkeley & Stanford

  https://people.eecs.berkeley.edu/~jhoffman/

• Fuzhen Zhuang @ ICT, CAS

  http://www.intsci.ac.cn/users/zhuangfuzhen/

• Fei Sha @ USC

  https://viterbi-web.usc.edu/~feisha/

课程

• 台湾大学李宏毅的视频讲解(中文视频)
• 北京邮电大学迁移学习公开课

代码

• FINBERT: FINANCIAL SENTIMENT ANALYSIS WITH PRE-TRAINED LANGUAGE MODELS
• Meta-Learning Acquisition Functions for Transfer Learning in Bayesian Optimization
• Online Knowledge Distillation with Diverse Peers
• Transfer Learning via Minimizing the Performance Gap Between Domains
• TANDA: Transfer and Adapt Pre-Trained Transformer Models for Answer Sentence Selection
• Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer
• Breast Cancer Diagnosis with Transfer Learning and Global Pooling
• Cross-lingual Dependency Parsing with Unlabeled Auxiliary Languages
• The Woman Worked as a Babysitter: On Biases in Language Generation
• Transfer Learning Between Related Tasks Using Expected Label Proportions
• hULMonA: The Universal Language Model in Arabic
• A Neural Grammatical Error Correction System Built On Better Pre-training and Sequential Transfer Learning
• Celebrity Profiling
• Evaluating Protein Transfer Learning with TAPE
• Fast and Flexible Multi-Task Classification Using Conditional Neural Adaptive Processes
• Cross-View Policy Learning for Street Navigation
• Transfer Learning in Biomedical Natural Language Processing: An Evaluation of BERT and ELMo on Ten Benchmarking Datasets
• Stability of Graph Scattering Transforms

数据集

• MNIST vs MNIST-M vs SVHN vs Synth vs USPS: digit images
• GTSRB vs Syn Signs : traffic sign recognition datasets, transfer between real and synthetic signs.
• NYU Depth Dataset V2: labeled paired images taken with two different cameras (normal and depth)
• CelebA: faces of celebrities, offering the possibility to perform gender or hair color translation for instance
• Office-Caltech dataset: images of office objects from 10 common categories shared by the Office-31 and Caltech-256 datasets. There are in total four domains: Amazon, Webcam, DSLR and Caltech.
• Cityscapes dataset: street scene photos (source) and their annoted version (target)
• UnityEyes vs MPIIGaze: simulated vs real gaze images (eyes)
• CycleGAN datasets: horse2zebra, apple2orange, cezanne2photo, monet2photo, ukiyoe2photo, vangogh2photo, summer2winter
• pix2pix dataset: edges2handbags, edges2shoes, facade, maps
• RaFD: facial images with 8 different emotions (anger, disgust, fear, happiness, sadness, surprise, contempt, and neutral). You can transfer a face from one emotion to another.
• VisDA 2017 classification dataset: 12 categories of object images in 2 domains: 3D-models and real images.
• Office-Home dataset: images of objects in 4 domains: art, clipart, product and real-world.
• DukeMTMC-reid and Market-1501: two pedestrian datasets collected at different places. The evaluation metric is based on open-set image retrieval.
• Amazon review benchmark dataset: sentiment analysis for four kinds (domains) of reviews: books, DVDs, electronics, kitchen
• ECML/PKDD Spam Filtering: emails from 3 different inboxes, that can represent the 3 domains.
• 20 Newsgroup: collection of newsgroup documents across 6 top categories and 20 subcategories. Subcategories can play the role of the domains, as describe in this article.

实战

• 基于深度学习和迁移学习的识花实践 Using Transfer Learning for Flower Recognition
• 基于Pytorch的图像分类 Using Transfer Learning for Image Classification
• 使用Pytorch进行finetune Using Pytorch for Fine-tune
• 英伟达迁移学习工具包

---

初步版本，水平有限，有错误或者不完善的地方，欢迎大家提建议和补充，会一直保持更新，本文为专知内容组原创内容，未经允许不得转载，如需转载请发送邮件至fangquanyi@gmail.com 或 联系微信专知小助手（Rancho_Fang）

敬请关注http://www.zhuanzhi.ai 和关注专知公众号，获取第一手AI相关知识

最近更新：2019-12-09