知识荟萃
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
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
-
Lixin Duan @ UESTC
-
Mingsheng Long @ THU
-
Judy Hoffman @ UC Berkeley & Stanford
-
Fuzhen Zhuang @ ICT, CAS
-
Fei Sha @ USC
课程
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
VIP内容
通过调整预训练的机器学习模型来解决特殊问题，在时间内建立自定义NLP模型。
在自然语言处理迁移学习中，您将学习:
- 用新的领域数据对预训练的模型进行微调
- 选择正确的模型来减少资源的使用
- 用于神经网络结构的迁移学习
- 生成文本与生成预先训练的Transformers
- BERT跨语言迁移学习
- 探索自然语言处理学术文献的基础
https://www.manning.com/books/transfer-learning-for-natural-language-processing
从头开始训练深度学习NLP模型是昂贵的、耗时的，并且需要大量的数据。在自然语言处理的迁移学习中，DARPA研究员Paul Azunre揭示了前沿的迁移学习技术，可以将可定制的预训练模型应用到您自己的NLP架构中。您将学习如何使用迁移学习为语言理解提供最先进的结果，即使使用有限的标签数据。最重要的是，您将节省训练时间和计算成本。
关于本书：
自然语言处理迁移学习教你通过构建现有的预训练模型快速创建强大的NLP解决方案。这是一本非常有用的书，书中提供了一些非常清晰的概念解释，你需要这些概念来学习转学，同时也提供了一些实际的例子，这样你就可以马上练习你的新技能。随着您的学习，您将应用最先进的迁移学习方法来创建垃圾邮件分类器、事实检查器和更多的现实世界的应用程序。
成为VIP会员查看完整内容
【百度提取码: ef2e】Transfer Learning for Natural Language Processing ，266页pdf
热门内容
最新内容
最新论文
With the rapid development of deep learning technology and improvement in computing capability, deep learning has been widely used in the field of hyperspectral image (HSI) classification. In general, deep learning models often contain many trainable parameters and require a massive number of labeled samples to achieve optimal performance. However, in regard to HSI classification, a large number of labeled samples is generally difficult to acquire due to the difficulty and time-consuming nature of manual labeling. Therefore, many research works focus on building a deep learning model for HSI classification with few labeled samples. In this article, we concentrate on this topic and provide a systematic review of the relevant literature. Specifically, the contributions of this paper are twofold. First, the research progress of related methods is categorized according to the learning paradigm, including transfer learning, active learning and few-shot learning. Second, a number of experiments with various state-of-the-art approaches has been carried out, and the results are summarized to reveal the potential research directions. More importantly, it is notable that although there is a vast gap between deep learning models (that usually need sufficient labeled samples) and the HSI scenario with few labeled samples, the issues of small-sample sets can be well characterized by fusion of deep learning methods and related techniques, such as transfer learning and a lightweight model. For reproducibility, the source codes of the methods assessed in the paper can be found at https://github.com/ShuGuoJ/HSI-Classification.git.
