入门教程

Domain adaptation，DA，中文可翻译为域适配、域匹配、域适应，是迁移学习中的一类非常重要的问题，也是一个持续的研究热点。Domain adaptation可用于计算机视觉、物体识别、文本分类、声音识别等常见应用中。这个问题的基本定义是，假设源域和目标域的类别空间一样，特征空间也一样，但是数据的分布不一样，如何利用有标定的源域数据，来学习目标域数据的标定？

事实上，根据目标域中是否有少量的标定可用，可以将domain adaptation大致分为无监督（目标域中完全无label）和半监督（目标域中有少量label）两大类。我们这里偏重介绍无监督。

形式化

给定：有标定的$\mathcal{D}{S}={X{S_i},Y_{S_i}}^{n}{i=1}$，以及无标定的$\mathcal{D}{T}={X_{T_i},?}^{m}_{i=1}$

求：$\mathcal{D}{T}$的标定$Y{T}$ （在实验环境中$\mathcal{D}_{T}$是有标定的，仅用来测试算法精度)

条件：

• $X_{S},X_{T} \in \mathbf{R}^{p \times d}$，即源域和目标域的特征空间相同（都是$d)维）

• ${Y_{S}}={Y_{T}}$，即源域和目标域的类别空间相同

• $P(X_{S})\ne P(X_T)$，即源域和目标域的数据分布不同

  例子

  比如说，同样都是一台电脑，在不同角度，不同光照，以及不同背景下拍照，图像的数据具有不同的分布，但是从根本上来说，都是一台电脑的图像。Domain adaptation要做的就是，如何根据这些不同分布的数据，很好地学习缺失的标定。

  

---

综述

• Arxiv

  • A Comprehensive Survey on Transfer Learning [7 Nov 2019]
  • Transfer Adaptation Learning: A Decade Survey [12 Mar 2019]
  • A review of single-source unsupervised domain adaptation [16 Jan 2019]
  • An introduction to domain adaptation and transfer learning [31 Dec 2018]
  • A Survey of Unsupervised Deep Domain Adaptation [6 Dec 2018]
  • Transfer Learning for Cross-Dataset Recognition: A Survey [2017]
  • Domain Adaptation for Visual Applications: A Comprehensive Survey [2017]

• 期刊

  • Deep Visual Domain Adaptation: A Survey [Neurocomputing 2018]
  • A Survey on Deep Transfer Learning [ICANN2018]
  • Visual domain adaptation: A survey of recent advances [2015]

理论

• Arxiv

  • A General Upper Bound for Unsupervised Domain Adaptation [3 Oct 2019]
  • On Deep Domain Adaptation: Some Theoretical Understandings [arXiv 15 Nov 2018]

• 会议

  • Bridging Theory and Algorithm for Domain Adaptation [ICML2019] [Pytorch]
  • On Learning Invariant Representation for Domain Adaptation [ICML2019] [code]
  • Learning Bounds for Domain Adaptation [NIPS2007]
  • Analysis of Representations for Domain Adaptation [NIPS2006]

• 期刊

  • A theory of learning from different domains [ML2010]

论文

Unsupervised DA

• Adversarial Methods

  • Arxiv

    • Reducing Domain Gap via Style-Agnostic Networks [25 Oct 2019]
    • Generalized Domain Adaptation with Covariate and Label Shift CO-ALignment [23 Oct 2019]
    • Adversarial Variational Domain Adaptation [25 Sep 2019]
    • Contrastively Smoothed Class Alignment for Unsupervised Domain Adaptation [arXiv 13 Sep 2019]
    • SALT: Subspace Alignment as an Auxiliary Learning Task for Domain Adaptation [arXiv 11 Jun 2019]
    • Joint Semantic Domain Alignment and Target Classifier Learning for Unsupervised Domain Adaptation [arXiv 10 Jun 2019]
    • Adversarial Domain Adaptation Being Aware of Class Relationships [arXiv 28 May 2019]
    • Domain-Invariant Adversarial Learning for Unsupervised Domain Adaption [arXiv 30 Nov 2018]
    • Unsupervised Domain Adaptation using Deep Networks with Cross-Grafted Stacks [arXiv 17 Feb 2019]
    • DART: Domain-Adversarial Residual-Transfer Networks for Unsupervised Cross-Domain Image Classification [arXiv 30 Dec 2018]
    • Unsupervised Domain Adaptation using Generative Models and Self-ensembling [arXiv 2 Dec 2018]
    • Domain Confusion with Self Ensembling for Unsupervised Adaptation [arXiv 10 Oct 2018]
    • Improving Adversarial Discriminative Domain Adaptation [arXiv 10 Sep 2018]
    • M-ADDA: Unsupervised Domain Adaptation with Deep Metric Learning [arXiv 6 Jul 2018] [Pytorch(official)]
    • Factorized Adversarial Networks for Unsupervised Domain Adaptation [arXiv 4 Jun 2018]
    • DiDA: Disentangled Synthesis for Domain Adaptation [arXiv 21 May 2018]
    • Unsupervised Domain Adaptation with Adversarial Residual Transform Networks [arXiv 25 Apr 2018]
    • Causal Generative Domain Adaptation Networks [arXiv 28 Jun 2018]

  • Conference

    • Discriminative Adversarial Domain Adaptation [AAAI2020]
    • Unifying Unsupervised Domain Adaptation and Zero-Shot Visual Recognition [IJCNN2019] [Matlab]
    • Transfer Learning with Dynamic Adversarial Adaptation Network [ICDM2019]
    • Joint Adversarial Domain Adaptation [ACM MM2019]
    • Cycle-consistent Conditional Adversarial Transfer Networks [ACM MM2019] [Pytorch]
    • Learning Disentangled Semantic Representation for Domain Adaptation [IJCAI2019] [Tensorflow]
    • Transferability vs. Discriminability: Batch Spectral Penalization for Adversarial Domain Adaptation [ICML2019] [Pytorch]
    • Transferable Adversarial Training: A General Approach to Adapting Deep Classifiers [ICML2019] [Pytorch]
    • Drop to Adapt: Learning Discriminative Features for Unsupervised Domain Adaptation [ICCV2019] [PyTorch]
    • Cluster Alignment with a Teacher for Unsupervised Domain Adaptation [ICCV2019] [Tensorflow]
    • Unsupervised Domain Adaptation via Regularized Conditional Alignment [ICCV2019]
    • Attending to Discriminative Certainty for Domain Adaptation [CVPR2019] [Project]
    • GCAN: Graph Convolutional Adversarial Network for Unsupervised Domain Adaptation [CVPR2019]
    • Domain-Symmetric Networks for Adversarial Domain Adaptation [CVPR2019] [Pytorch]
    • DLOW: Domain Flow for Adaptation and Generalization [CVPR2019 Oral]
    • Progressive Feature Alignment for Unsupervised Domain Adaptation [CVPR2019]
    • Gotta Adapt ’Em All: Joint Pixel and Feature-Level Domain Adaptation for Recognition in the Wild [CVPR2019]
    • Looking back at Labels: A Class based Domain Adaptation Technique [IJCNN2019] [Project]
    • Consensus Adversarial Domain Adaptation [AAAI2019]
    • Transferable Attention for Domain Adaptation [AAAI2019]
    • Exploiting Local Feature Patterns for Unsupervised Domain Adaptation [AAAI2019]
    • Augmented Cyclic Adversarial Learning for Low Resource Domain Adaptation [ICLR2019]
    • Conditional Adversarial Domain Adaptation [NIPS2018] [Pytorch(official)] [Pytorch(third party)]
    • Semi-supervised Adversarial Learning to Generate Photorealistic Face Images of New Identities from 3D Morphable Model [ECCV2018]
    • Deep Adversarial Attention Alignment for Unsupervised Domain Adaptation: the Benefit of Target Expectation Maximization [ECCV2018]
    • Learning Semantic Representations for Unsupervised Domain Adaptation [ICML2018] [TensorFlow(Official)]
    • CyCADA: Cycle-Consistent Adversarial Domain Adaptation [ICML2018] [Pytorch(official)]
    • From source to target and back: Symmetric Bi-Directional Adaptive GAN [CVPR2018] [Keras(Official)] [Pytorch]
    • Detach and Adapt: Learning Cross-Domain Disentangled Deep Representation [CVPR2018] [Tensorflow]
    • Maximum Classifier Discrepancy for Unsupervised Domain Adaptation [CVPR2018] [Pytorch(Official)]
    • Adversarial Feature Augmentation for Unsupervised Domain Adaptation [CVPR2018] [TensorFlow(Official)]
    • Duplex Generative Adversarial Network for Unsupervised Domain Adaptation [CVPR2018] [Pytorch(Official)]
    • Generate To Adapt: Aligning Domains using Generative Adversarial Networks [CVPR2018] [Pytorch(Official)]
    • Image to Image Translation for Domain Adaptation [CVPR2018]
    • Unsupervised Domain Adaptation with Similarity Learning [CVPR2018]
    • Conditional Generative Adversarial Network for Structured Domain Adaptation [CVPR2018]
    • Collaborative and Adversarial Network for Unsupervised Domain Adaptation [CVPR2018] [Pytorch]
    • Re-Weighted Adversarial Adaptation Network for Unsupervised Domain Adaptation [CVPR2018]
    • Multi-Adversarial Domain Adaptation [AAAI2018] [Caffe(Official)]
    • Wasserstein Distance Guided Representation Learning for Domain Adaptation [AAAI2018] [TensorFlow(official)] [Pytorch]
    • Incremental Adversarial Domain Adaptation for Continually Changing Environments [ICRA2018]
    • Adversarial Dropout Regularization [ICLR2018]
    • A DIRT-T Approach to Unsupervised Domain Adaptation [ICLR2018 Poster] [Tensorflow(Official)]
    • Label Efficient Learning of Transferable Representations acrosss Domains and Tasks [NIPS2017] [Project]
    • Adversarial Discriminative Domain Adaptation [CVPR2017] [Tensorflow(Official)] [Pytorch]
    • Unsupervised Pixel–Level Domain Adaptation with Generative Adversarial Networks [CVPR2017] [Tensorflow(Official)] [Pytorch]
    • Domain Separation Networks [NIPS2016]
    • Deep Reconstruction-Classification Networks for Unsupervised Domain Adaptation [ECCV2016]
    • Domain-Adversarial Training of Neural Networks [JMLR2016]
    • Unsupervised Domain Adaptation by Backpropagation [ICML2015] [Caffe(Official)] [Tensorflow] [Pytorch]

  • Journal

    • Adversarial Learning and Interpolation Consistency for Unsupervised Domain Adaptation [IEEE ACCESS]
    • TarGAN: Generating target data with class labels for unsupervised domain adaptation [Knowledge-Based Systems]

• Distance-based Methods

  • Journal

    • Transferable Representation Learning with Deep Adaptation Networks [TPAMI]

  • Conference

    • Normalized Wasserstein for Mixture Distributions With Applications in Adversarial Learning and Domain Adaptation [ICCV2019]
    • Joint Domain Alignment and Discriminative Feature Learning for Unsupervised Deep Domain Adaptation [AAAI2019]
    • Residual Parameter Transfer for Deep Domain Adaptation [CVPR2018]
    • Deep Asymmetric Transfer Network for Unbalanced Domain Adaptation [AAAI2018]
    • Deep CORAL: Correlation Alignment for Deep Domain Adaptation [ECCV2016]
    • Learning Transferable Features with Deep Adaptation Networks [ICML2015][code]
    • Unsupervised Domain Adaptation with Residual Transfer Networks [NIPS2016] [code]
    • Deep Transfer Learning with Joint Adaptation Networks [ICML2017] [code]

  • Arxiv

    • Deep Domain Confusion: Maximizing for Domain Invariance [Arxiv 2014]

• Optimal Transport

  • CDOT: Continuous Domain Adaptation using Optimal Transport [20 Sep 2019]
  • Differentially Private Optimal Transport: Application to Domain Adaptation [IJCAI]
  • DeepJDOT: Deep Joint distribution optimal transport for unsupervised domain adaptation [ECCV2018] [Keras]
  • Joint Distribution Optimal Transportation for Domain Adaptation [NIPS2017] [python] [Python Optimal Transport Library]

• Incremental Methods

  • Incremental Adversarial Domain Adaptation for Continually Changing Environments [ICRA2018]
  • Continuous Manifold based Adaptation for Evolving Visual Domains [CVPR2014]

• Other Methods

  • Arxiv

    • Improving Unsupervised Domain Adaptation with Variational Information Bottleneck [21 Nov 2019]
    • Deep causal representation learning for unsupervised domain adaptation [28 Oct 2019]
    • Domain-invariant Learning using Adaptive Filter Decomposition [25 Sep 2019]
    • Discriminative Clustering for Robust Unsupervised Domain Adaptation [arXiv 30 May 2019]
    • Virtual Mixup Training for Unsupervised Domain Adaptation [arXiv on 24 May 2019] [Tensorflow]
    • Learning Smooth Representation for Unsupervised Domain Adaptation [arXiv 26 May 2019]
    • Towards Self-similarity Consistency and Feature Discrimination for Unsupervised Domain Adaptation [arXiv 13 Apr 2019]
    • Easy Transfer Learning By Exploiting Intra-domain Structures [arXiv 2 Apr 2019]
    • Domain Discrepancy Measure Using Complex Models in Unsupervised Domain Adaptation [arXiv 30 Jan 2019]
    • Domain Alignment with Triplets [arXiv 22 Jan 2019]
    • Deep Discriminative Learning for Unsupervised Domain Adaptation [arXiv 17 Nov 2018]

  • Conference

    • Unsupervised Domain Adaptation via Structured Prediction Based Selective Pseudo-Labeling [AAAI2020]
    • CUDA: Contradistinguisher for Unsupervised Domain Adaptation [ICDM2019]
    • Domain Adaptation with Asymmetrically-Relaxed Distribution Alignment [ICML2019]
    • Batch Weight for Domain Adaptation With Mass Shift [ICCV2019]
    • Switchable Whitening for Deep Representation Learning [ICCV2019] [pytorch]
    • Confidence Regularized Self-Training [ICCV2019 Oral] [Pytorch]
    • Larger Norm More Transferable: An Adaptive Feature Norm Approach for Unsupervised Domain Adaptation [ICCV2019] [Pytorch(official)]
    • Transferrable Prototypical Networks for Unsupervised Domain Adaptation [CVPR2019(Oral)]
    • Sliced Wasserstein Discrepancy for Unsupervised Domain Adaptation [CVPR2019]
    • Unsupervised Domain Adaptation using Feature-Whitening and Consensus Loss [CVPR 2019] [Pytorch]
    • Domain Specific Batch Normalization for Unsupervised Domain Adaptation [CVPR2019]
    • AdaGraph: Unifying Predictive and Continuous Domain Adaptation through Graphs [CVPR2019] [Pytorch]
    • Unsupervised Visual Domain Adaptation: A Deep Max-Margin Gaussian Process Approach [CVPR2019] [Project]
    • Contrastive Adaptation Network for Unsupervised Domain Adaptation [CVPR2019] [Pytorch]
    • Distant Supervised Centroid Shift: A Simple and Efficient Approach to Visual Domain Adaptation [CVPR2019]
    • Unsupervised Domain Adaptation via Calibrating Uncertainties [CVPRW2019]
    • Bayesian Uncertainty Matching for Unsupervised Domain Adaptation [IJCAI2019]
    • Unsupervised Domain Adaptation for Distance Metric Learning [ICLR2019]
    • Co-regularized Alignment for Unsupervised Domain Adaptation [NIPS2018]
    • Domain Invariant and Class Discriminative Feature Learning for Visual Domain Adaptation [TIP 2018]
    • Graph Adaptive Knowledge Transfer for Unsupervised Domain Adaptation [ECCV2018]
    • Aligning Infinite-Dimensional Covariance Matrices in Reproducing Kernel Hilbert Spaces for Domain Adaptation [CVPR2018]
    • Unsupervised Domain Adaptation with Distribution Matching Machines [AAAI2018]
    • Learning to cluster in order to transfer across domains and tasks [ICLR2018] [Bolg] [Pytorch]
    • Self-Ensembling for Visual Domain Adaptation [ICLR2018]
    • Minimal-Entropy Correlation Alignment for Unsupervised Deep Domain Adaptation [ICLR2018] [TensorFlow]
    • Associative Domain Adaptation [ICCV2017] [TensorFlow] [Pytorch]
    • AutoDIAL: Automatic DomaIn Alignment Layers [ICCV2017]
    • Asymmetric Tri-training for Unsupervised Domain Adaptation [ICML2017] [TensorFlow]
    • Learning Transferrable Representations for Unsupervised Domain Adaptation [NIPS2016]

  • Journal

    • Adaptive Batch Normalization for practical domain adaptation [Pattern Recognition(2018)]
    • Unsupervised Domain Adaptation by Mapped Correlation Alignment [IEEE ACCESS]

Semi-supervised DA

• Arxiv

  • Reducing Domain Gap via Style-Agnostic Networks [25 Oct 2019]

• Conference

  • Semi-supervised Domain Adaptation via Minimax Entropy [ICCV2019] [Pytorch]

Weakly-Supervised DA

• Arxiv

  • Butterfly: Robust One-step Approach towards Wildly-unsupervised Domain Adaptation [arXiv on 19 May 2019]

• Conference

  • Weakly Supervised Open-set Domain Adaptation by Dual-domain Collaboration [CVPR2019]
  • Transferable Curriculum for Weakly-Supervised Domain Adaptation [AAAI2019]

Zero-shot DA

• Zero-shot Domain Adaptation Based on Attribute Information [ACML2019]
• Conditional Coupled Generative Adversarial Networks for Zero-Shot Domain Adaptation [ICCV2019]
• Generalized Zero-Shot Learning with Deep Calibration Network NIPS2018
• Zero-Shot Deep Domain Adaptation [ECCV2018]

One-shot DA

• One-Shot Imitation from Observing Humans via Domain-Adaptive Meta-Learning [arxiv]
• One-Shot Adaptation of Supervised Deep Convolutional Models [ICLR Workshop 2014]

Few-shot DA

• d-SNE: Domain Adaptation using Stochastic Neighborhood Embedding [CVPR2019 Oral]
• Few-Shot Adversarial Domain Adaptation [NIPS2017]

Open Set DA

• Arxiv

  • Known-class Aware Self-ensemble for Open Set Domain Adaptation [arXiv 3 May 2019]

• Conference

  • Separate to Adapt: Open Set Domain Adaptation via Progressive Separation [CVPR2019]
  • Weakly Supervised Open-set Domain Adaptation by Dual-domain Collaboration [CVPR2019]
  • Learning Factorized Representations for Open-set Domain Adaptation [ICLR2019]
  • Open Set Domain Adaptation by Backpropagation [ECCV2018] [Pytorch(Official)] [Tensorflow] [Pytorch]

• Open Set Domain Adaptation [ICCV2017]

Partial DA

• Arxiv
  • Tackling Partial Domain Adaptation with Self-Supervision [arXiv 12 Jun 2019]
  • Selective Transfer with Reinforced Transfer Network for Partial Domain Adaptation [arXiv 26 May 2019]
  • Domain Adversarial Reinforcement Learning for Partial Domain Adaptation [arXiv 10 May 2019]
• Conference
  • Learning to Transfer Examples for Partial Domain Adaptation [CVPR2019]
  • Partial Adversarial Domain Adaptation [ECCV2018] [Pytorch(Official)]
  • Importance Weighted Adversarial Nets for Partial Domain Adaptation [CVPR2018]
  • Partial Transfer Learning with Selective Adversarial Networks [CVPR2018][paper weekly] [Pytorch(Official) & Caffe(official)]

Universal DA

• Conference
  • Universal Domain Adaptation [CVPR2019] [Pytorch]

Multi Source DA

• Arxiv

  • Multi-Source Domain Adaptation and Semi-Supervised Domain Adaptation with Focus on Visual Domain Adaptation Challenge 2019 [14 Oct 2019]

• Conference

  • Multi-source Distilling Domain Adaptation [AAAI2020] [code]
  • Multi-source Domain Adaptation for Semantic Segmentation [NeurlPS2019]
  • Moment Matching for Multi-Source Domain Adaptation [ICCV2019] [Pytorch]
  • Multi-Domain Adversarial Learning [ICLR2019]
  • Algorithms and Theory for Multiple-Source Adaptation [NIPS2018]
  • Adversarial Multiple Source Domain Adaptation [NIPS2018] [Pytorch]
  • Boosting Domain Adaptation by Discovering Latent Domains [CVPR2018]
  • Deep Cocktail Network: Multi-source Unsupervised Domain Adaptation with Category Shift [CVPR2018] [Pytorch]

• Journal

  • A survey of multi-source domain adaptation [Information Fusion]

Multi Target DA

• Unsupervised Multi-Target Domain Adaptation: An Information Theoretic Approach [arXiv]

Multi Step DA

• Arxiv

  • Adversarial Domain Adaptation for Stance Detection [arXiv]
  • Ensemble Adversarial Training: Attacks and Defenses [arXiv]

• Conference

  • Distant domain transfer learning [AAAI2017]

Heterogeneous DA

• Heterogeneous Domain Adaptation via Soft Transfer Network [ACM MM2019]

Target-agnostic DA

• Arxiv

  • Compound Domain Adaptation in an Open World [8 Sep 2019]

• Conference

  • Domain Agnostic Learning with Disentangled Representations [ICML2019] [Pytorch]
  • Blending-target Domain Adaptation by Adversarial Meta-Adaptation Networks [CVPR2019] [Pytorch]

Federated DA

• Arxiv
  • Federated Adversarial Domain Adaptation [5 Nov 2019]

Model Selection

• Towards Accurate Model Selection in Deep Unsupervised Domain Adaptation [ICML2019] [Pytorch]

教程Tutorial

• 迁移学习中的领域自适应方法[PPT][视频]

代码

• Bridging Theory and Algorithm for Domain Adaptation [ICML2019] [Pytorch]

• Cycle-consistent Conditional Adversarial Transfer Networks [ACM MM2019] [Pytorch]

• Learning Disentangled Semantic Representation for Domain Adaptation [IJCAI2019] [Tensorflow]

• Transferability vs. Discriminability: Batch Spectral Penalization for Adversarial Domain Adaptation [ICML2019] [Pytorch]

• Transferable Adversarial Training: A General Approach to Adapting Deep Classifiers [ICML2019] [Pytorch]

• Drop to Adapt: Learning Discriminative Features for Unsupervised Domain Adaptation [ICCV2019] [PyTorch]

• Cluster Alignment with a Teacher for Unsupervised Domain Adaptation [ICCV2019] [Tensorflow]

• Domain-Symmetric Networks for Adversarial Domain Adaptation [CVPR2019] [Pytorch]

• CyCADA: Cycle-Consistent Adversarial Domain Adaptation [ICML2018] [Pytorch(official)]

• From source to target and back: Symmetric Bi-Directional Adaptive GAN [CVPR2018] [Keras(Official)] [Pytorch]

• Detach and Adapt: Learning Cross-Domain Disentangled Deep Representation [CVPR2018] [Tensorflow]

• Maximum Classifier Discrepancy for Unsupervised Domain Adaptation [CVPR2018] [Pytorch(Official)]

• Adversarial Feature Augmentation for Unsupervised Domain Adaptation [CVPR2018] [TensorFlow(Official)]

• Duplex Generative Adversarial Network for Unsupervised Domain Adaptation [CVPR2018] [Pytorch(Official)]

• Generate To Adapt: Aligning Domains using Generative Adversarial Networks [CVPR2018] [Pytorch(Official)]

• Learning Transferable Features with Deep Adaptation Networks [ICML2015][caffe]

• Unsupervised Domain Adaptation with Residual Transfer Networks [NIPS2016] [caffe]

• Deep Transfer Learning with Joint Adaptation Networks [ICML2017] [PyTorch]

数据集

• Office-Caltech10

  • Download Office+Caltech original images [Baiduyun]
  • Download Office+Caltech SURF dataset [MEGA|Baiduyun]
  • Download Office+Caltech DeCAF dataset [MEGA|Baiduyun]

• Office-31

  • Download Office-31 raw images | Download from MEGA
  • Download Office-31 DeCAF6 and DeCAF7 features
  • Download Office-31 DeCAF features by Frame
  • Download Office-31 SURF features
  • Download Office-31 ResNet-50 features | Download from MEGA

• Office-Home

  • Download Office-Home original images
  • Download Office-Home ResNet-50 pretrained features | Download from MEGA

• ImageCLEF

  • Download the ImageCLEF dataset
  • Download Image-CLEF ResNet-50 pretrained features | Download from MEGA

• USPS+MNIST

  • Download MNIST+USPS SURF dataset [MEGA|Baiduyun]

• VisDA-17

  • Download the VisDA-classification dataset
  • Download the VisDA-segmentation dataset
  • Download VisDA classification dataset features by ResNet-50 | Download from MEGA

• Amazon review

  • Download Amazon review dataset

• Cross-dataset Testbed

  • Download the Cross-dataset testbed

• COIL20

  • Download COIL20 SURF dataset [MEGA|Baiduyun]

• CMU-PIE

  • Download PIE SURF dataset [MEGA|Baiduyun]

• VLSC

  • Download the VLSC DeCAF dataset [MEGA|Baiduyun]

• Animals-with-Attributes

  • Download the SURF/SIFT/DeCAF features [MEGA|Baiduyun]

领域专家

• 应用研究

  • Qiang Yang @ HKUST

    迁移学习领域权威大牛。他所在的课题组基本都做迁移学习方面的研究。迁移学习综述《A survey on transfer learning》就出自杨强老师课题组。他的学生们：

    1). Sinno J. Pan

    现为老师，详细介绍见第二条。

    2). Ben Tan

    主要研究传递迁移学习(transitive transfer learning)。代表文章：

    • Transitive Transfer Learning. KDD 2015.
    • Distant Domain Transfer Learning. AAAI 2017.

    3). Derek Hao Hu

    主要研究迁移学习与行为识别结合，目前在Snap公司。代表文章：

    • Transfer Learning for Activity Recognition via Sensor Mapping. IJCAI 2011.
    • Cross-domain activity recognition via transfer learning. PMC 2011.
    • Bridging domains using world wide knowledge for transfer learning. TKDE 2010.

    4). Vencent Wencheng Zheng

    也做行为识别与迁移学习的结合，目前在新加坡一个研究所当研究科学家。

    代表文章：

    • User-dependent Aspect Model for Collaborative Activity Recognition. IJCAI 2011.
    • Transfer Learning by Reusing Structured Knowledge. AI Magazine.
    • Transferring Multi-device Localization Models using Latent Multi-task Learning. AAAI 2008.
    • Transferring Localization Models Over Time. AAAI 2008.
    • Cross-Domain Activity Recognition. Ubicomp 2009.
    • Collaborative Location and Activity Recommendations with GPS History Data. WWW 2010.

    5). Ying Wei

    做迁移学习与数据挖掘相关的研究。代表工作：

    • Instilling Social to Physical: Co-Regularized Heterogeneous Transfer Learning. AAAI 2016.

    • Transfer Knowledge between Cities. KDD 2016

    其他还有很多学生都做迁移学习方面的研究，更多请参考杨强老师主页。

  • 2. Sinno J. Pan @ NTU

    杨强老师学生，比较著名的工作是TCA方法。现在在NTU当老师，一直都在做迁移学习研究。代表工作：

    • A Survey On Transfer Learning. TKDE 2010.
    • Domain Adaptation via Transfer Component Analysis. TNNLS 2011. [著名的TCA方法]
    • Cross-domain sentiment classification via spectral feature alignment. WWW 2010. [著名的SFA方法]
    • Transferring Localization Models across Space. AAAI 2008.
  • 3. Lixin Duan @ UESTC

    毕业于NTU，现在在UESTC当老师。代表工作：

    • Domain Transfer Multiple Kernel Learning. PAMI 2012.
    • Visual Event Recognition in Videos by Learning from Web Data. PAMI 2012.
  • 4. Mingsheng Long @ THU

    毕业于清华大学，现在在清华大学当老师，一直在做迁移学习方面的工作。代表工作：

    • Dual Transfer Learning. SDM 2012.
    • Transfer Feature Learning with Joint Distribution Adaptation. ICCV 2013.
    • Transfer Joint Matching for Unsupervised Domain Adaptation. CVPR 2014.
    • Learning transferable features with deep adaptation networks. ICML 2015. [著名的DAN方法]
    • Deep Transfer Learning with Joint Adaptation Networks. ICML 2017.
  • 5. Judy Hoffman @ UC Berkeley & Stanford

    Feifei Li的博士后，现在当老师。她有个学生叫做Eric Tzeng，做深度迁移学习。代表工作：

    • Simultaneous Deep Transfer Across Domains and Tasks. ICCV 2015.
    • Deep Domain Confusion: Maximizing for Domain Invariance. arXiv 2014.
    • Adversarial Discriminative Domain Adaptation. arXiv 2017.
  • 6. Fuzhen Zhuang @ ICT, CAS

    中科院计算所当老师，主要做迁移学习与文本结合的研究。代表工作：

    • Transfer Learning from Multiple Source Domains via Consensus Regularization. CIKM 2008.
  • 7. Kilian Q. Weinberger @ Cornell U.

    现在康奈尔大学当老师。Minmin Chen是他的学生。代表工作：

    • Distance metric learning for large margin nearest neighbor classification. JMLR 2009.
    • Feature hashing for large scale multitask learning. ICML 2009.
    • An introduction to nonlinear dimensionality reduction by maximum variance unfolding. AAAI 2006. [著名的MVU方法]
    • Co-training for domain adaptation. NIPS 2011. [著名的Co-training方法]
  • 8. Fei Sha @ USC

    USC教授。学生Boqing Gong提出了著名的GFK方法。代表工作：

    • Connecting the Dots with Landmarks: Discriminatively Learning Domain-Invariant Features for Unsupervised Domain Adaptation. ICML 2013.
    • Geodesic flow kernel for unsupervised domain adaptation. CVPR 2012. [著名的GFK方法]
  • 9. Mahsa Baktashmotlagh @ U. Quessland

    现在当老师。主要做流形学习与domain adaptation结合。代表工作：

    • Unsupervised Domain Adaptation by Domain Invariant Projection. ICCV 2013.
    • Domain Adaptation on the Statistical Manifold. CVPR 2014.
    • Distribution-Matching Embedding for Visual Domain Adaptation. JMLR 2016.
  • 10. Baochen Sun @ Microsoft

    现在在微软。著名的CoRAL系列方法的作者。代表工作：

    • Return of Frustratingly Easy Domain Adaptation. AAAI 2016.
    • Deep coral: Correlation alignment for deep domain adaptation. ECCV 2016.
  • 11. Wenyuan Dai

    著名的第四范式创始人，虽然不做研究了，但是当年求学时几篇迁移学习文章至今都很高引。代表工作：

    • Boosting for transfer learning. ICML 2007. [著名的TrAdaboost方法]
    • Self-taught clustering. ICML 2008.

• 理论研究

  • 1. Arthur Gretton @ UCL

       主要做two-sample test。代表工作：

    • A Kernel Two-Sample Test. JMLR 2013.
    • Optimal kernel choice for large-scale two-sample tests. NIPS 2012. [著名的MK-MMD]
  • 2. Shai Ben-David @ U.Waterloo

    很多迁移学习的理论工作由他给出。代表工作：

    • Analysis of representations for domain adaptation. NIPS 2007.
    • A theory of learning from different domains. Machine Learning 2010.
  • 3. Alex Smola @ CMU

    也是做一些机器学习的理论工作，和上面两位合作比较多。代表工作非常多，不列了。

  • 4. John Blitzer @ Google

    著名的SCL方法提出者，现在也在做机器学习。代表工作：

    • Domain adaptation with structural correspondence learning. ECML 2007. [著名的SCL方法]
  • 5. Yoshua Bengio @ U.Montreal

    深度学习领军人物，主要做深度迁移学习的一些理论工作。代表工作：

    • Deep Learning of Representations for Unsupervised and Transfer Learning. ICML 2012.
    • How transferable are features in deep neural networks? NIPS 2014.
    • Unsupervised and Transfer Learning Challenge: a Deep Learning Approach. ICML 2012.
  • 6. Geoffrey Hinton @ U.Toronto

    深度学习领军人物，也做深度迁移学习的理论工作。

    • Distilling the knowledge in a neural network. NIPS 2014.

---

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：2019-12-9