mynhervankoek / awesome-transfer-learning

Best transfer learning and domain adaptation resources (papers, tutorials, datasets, etc.)

Awesome Transfer Learning

A list of awesome papers and cool resources on transfer learning, domain adaptation and domain-to-domain translation in general! As you will notice, this list is currently mostly focused on domain adaptation (DA), but don't hesitate to suggest resources in other subfields of transfer learning. I accept pull requests.

Table of Contents

• Tutorial and Blogs
• Papers
  • Surveys
  • Theory
  • Unsupervised DA
    • Adversarial methods
    • Optimal Transport
    • Embedding methods
    • Kernel methods
    • Autoencoder approach
    • Subspace learning
    • Self-ensembling methods
    • Other
  • Semi-supervised DA
    • General methods
    • Subspace learning
    • Copulas methods
  • Few-shot supervised DA
    • Adversarial methods
    • Embedding methods
  • Applied DA
    • Physics
• Datasets
  • Image-to-image
  • Text-to-text
• Results
  • Digits transfer
• Challenges
• Libraries

Tutorials and Blogs

• Transfer Learning − Machine Learning's Next Frontier
• A Little Review of Domain Adaptation in 2017

Papers

Papers are ordered by theme and inside each theme by publication date (submission date for arXiv papers). If the network or algorithm is given a name in a paper, this one is written in bold before the paper's name.

Surveys

• A Survey on Transfer Learning (2009)
• A Survey of transfer learning (2016)
• Domain Adaptation for Visual Applications: A Comprehensive Survey (2017)

Theory

• A theory of learning from different domains (2010)

Unsupervised DA

Only the source domain can have labels

Adversarial methods

• DANN: Domain-Adversarial Training of Neural Networks (2015)
• JAN: Deep Transfer Learning with Joint Adaptation Networks (2016)
• CoGAN: Coupled Generative Adversarial Networks (2016)
• DRCN: Deep Reconstruction-Classification Networks for Unsupervised Domain Adaptation (2016)
• DSN: Domain Separation Networks (2016)
• DIAT: Deep Identity-aware Transfer of Facial Attributes (2016)
• DTN: Unsupervised Cross-domain Image Generation (2016)
• Learning to Pivot with Adversarial Networks (2016)
• Pix2pix: Image-to-Image Translation with Conditional Adversarial Networks (2016)
• SimGAN: Learning from Simulated and Unsupervised Images through Adversarial Training (2016) (2016)
• PixelDA: Unsupervised Pixel–Level Domain Adaptation with Generative Adversarial Networks (2016)
• ADDA: Adaptative Discriminative Domain Adaptation (2017)
• UNIT: Unsupervised Image-to-Image Translation Networks (2017)
• CycleGAN: Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks (2017)
• DiscoGAN: Learning to Discover Cross-Domain Relations with Generative Adversarial Networks (2017)
• DualGAN: DualGAN: Unsupervised Dual Learning for Image-to-Image Translation (2017)
• GenToAdapt: Generate To Adapt: Aligning Domains using Generative Adversarial Networks (2017)
• SBADA-GAN: From source to target and back: symmetric bi-directional adaptive GAN (2017)
• DistanceGAN: One-Sided Unsupervised Domain Mapping (2017)
• WDGRL: Wasserstein Distance Guided Representation Learning for Domain Adaptation (2017)
• Model F: Unsupervised Domain Adaptation for Face Recognition in Unlabeled Videos (2017)
• CyCADA: CyCADA: Cycle-Consistent Adversarial Domain Adaptation (2017)
• StarGAN: StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translation (2017)
• pix2pixHD: High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs (2018)
• XGAN: XGAN: Unsupervised Image-to-Image Translation for Many-to-Many Mappings (2017)
• BicycleGAN : Toward Multimodal Image-to-Image Translation (2017)
• Label Efficient Learning of Transferable Representations across Domains and Tasks (2017)
• DIRT-T: A DIRT-T Approach to Unsupervised Domain Adaptation (2017)
• ComboGAN: ComboGAN: Unrestrained Scalability for Image Domain Translation (2017)
• I2I: Image to Image Translation for Domain Adaptation (2017)
• AugCGAN: Augmented CycleGAN: Learning Many-to-Many Mappings from Unpaired Data (2018)
• RadialGAN: RadialGAN: Leveraging multiple datasets to improve target-specific predictive models using Generative Adversarial Networks (2018)
• MUNIT: Multimodal Unsupervised Image-to-Image Translation (2018)
• DupGAN: Duplex Generative Adversarial Network for Unsupervised Domain Adaptation (2018)
• Augmented-Cyc: Augmented Cyclic Adversarial Learning for Domain Adaptation (2018)
• MSTN: http://proceedings.mlr.press/v80/xie18c/xie18c.pdf (2018)

Optimal Transport

• OT: Optimal Transport for Domain Adaptation (2015)
• Theoretical Analysis of Domain Adaptation with Optimal Transport (2016)
• JDOT: Joint distribution optimal transportation for domain adaptation (2017)
• Monge map learning: Large Scale Optimal Transport and Mapping Estimation (2017)
• JCPOT: Optimal Transport for Multi-source Domain Adaptation under Target Shift (2018)
• DeepJDOT: DeepJDOT: Deep Joint distribution optimal transport for unsupervised domain adaptation (2018)

Embedding methods

• DA_assoc : Associative Domain Adaptation (2017)

Kernel methods

• SurK: Covariate Shift in Hilbert Space: A Solution via Surrogate Kernels (2015)
• DAN: Learning Transferable Features with Deep Adaptation Networks (2015)
• RTN: Unsupervised Domain Adaptation with Residual Transfer Networks (2016)
• Easy DA: A Simple Approach for Unsupervised Domain Adaptation (2016)

Autoencoder approach

• MCAE: Learning Classifiers from Synthetic Data Using a Multichannel Autoencoder (2015)
• SMCAE: Learning from Synthetic Data Using a Stacked Multichannel Autoencoder (2015)

Subspace Learning

• SGF: Domain Adaptation for Object Recognition: An Unsupervised Approach (2011)
• GFK: Geodesic Flow Kernel for Unsupervised Domain Adaptation (2012)
• SA: Unsupervised Visual Domain Adaptation Using Subspace Alignment (2015)
• CORAL: Return of Frustratingly Easy Domain Adaptation (2015)
• Deep CORAL: Deep CORAL: Correlation Alignment for Deep Domain Adaptation (2016)
• ILS: Learning an Invariant Hilbert Space for Domain Adaptation (2016)
• Log D-CORAL: Correlation Alignment by Riemannian Metric for Domain Adaptation (2017)

Self-Ensembling methods

• MT: Self-ensembling for domain adaptation (2017)

Other

• Adapting Visual Category Models to New Domains (2010)
• AdaBN: Revisiting Batch Normalization for Practical Domain Adaptation (2016)

Semi-supervised DA

All the source points are labelled, but only few target points are.

General methods

• da+lap-sim : Semi-Supervised Domain Adaptation with Instance Constraints (2013)

Subspace learning

• EA++: Co-regularization Based Semi-supervised Domain Adaptation (2010)
• SDASL: Semi-supervised Domain Adaptation with Subspace Learning for Visual Recognition (2015)

Copulas methods

• NPRV: Semi-Supervised Domain Adaptation with Non-Parametric Copulas (2013)

Few-shot supervised DA

Only a few target examples are available, but they are labelled

Adversarial methods

• FADA: Few-Shot Adversarial Domain Adaptation (2017)

Embedding methods

• CCSA: Unified Deep Supervised Domain Adaptation and Generalization (2017)

Applied DA

Domain adaptation applied to other fields, like physics or biology

Physics

• Learning to Pivot with Adversarial Networks (2016)

• Adversarial Domain Adaptation for Identifying Phase Transitions (2017)

• Identifying Quantum Phase Transitions with Adversarial Neural Networks (2017)

• Automated discovery of characteristic features of phase transitions in many-body localization (2017)

Datasets

Image-to-image

• 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.

Text-to-text

• 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.

Results

The results are indicated as the prediction accuracy (in %) in the target domain after adapting the source to the target. For the moment, they only correspond to the results given in the original papers, so the methodology may vary between each paper and these results must be taken with a grain of salt.

Digits transfer

Source Target	MNIST MNIST-M	Synth SVHN	MNIST SVHN	SVHN MNIST	MNIST USPS	USPS MNIST
SA	56.90	86.44	?	59.32	?	?
DANN	76.66	91.09	?	73.85	?	?
CoGAN	?	?	?	?	91.2	89.1
DRCN	?	?	40.05	81.97	91.80	73.67
DSN	83.2	91.2	?	82.7	?	?
DTN	?	?	90.66	79.72	?	?
PixelDA	98.2	?	?	?	95.9	?
ADDA	?	?	?	76.0	89.4	90.1
UNIT	?	?	?	90.53	95.97	93.58
GenToAdapt	?	?	?	92.4	95.3	90.8
SBADA-GAN	99.4	?	61.1	76.1	97.6	95.0
DAassoc	89.47	91.86	?	97.60	?	?
CyCADA	?	?	?	90.4	95.6	96.5
I2I	?	?	?	92.1	95.1	92.2
DIRT-T	98.7	?	76.5	99.4	?	?
DeepJDOT	92.4	?	?	96.7	95.7	96.4

Challenges

• Visual Domain Adaptation Challenge (VisDA)
• Open AI Retro Contest

Libraries

No good library for the moment (as far as I know). If you're interested in a project of creating a generic transfer learning/domain adaptation library, please let me know.