（转）Awsome Domain-Adaptation

Awsome Domain-Adaptation

2018-08-06 19:27:54

 

This blog is copied from: https://github.com/zhaoxin94/awsome-domain-adaptation 

 

This repo is a collection of AWESOME things about domian adaptation,including papers,code etc.Feel free to star and fork.

Contents

• Papers
  • Overview
  • Theory
  • Unsupervised DA
    • Adversarial Methods
    • Network Methods
    • Optimal Transport
    • Incremental Methods
    • Other Methods
  • Zero-shot DA
  • Few-shot DA
  • Image-to-Image Translation
  • Open Set DA
  • Partial DA
  • Multi-source DA
  • General Transfer Learning
  • Applications
    • Object Detection
    • Semantic Segmentation
    • Person Re-Identification
    • Others
  • Benchmarks

Papers

Overview

• Deep Visual Domain Adaptation: A Survey [arXiv 2018]
• Domain Adaptation for Visual Applications: A Comprehensive Survey [arXiv 2017]

Theory

• Analysis of Representations for Domain Adaptation [NIPS2006]
• A theory of learning from different domains [ML2010]
• Learning Bounds for Domain Adaptation [NIPS2007]

Unsupervised DA

Adversarial Methods

• M-ADDA: Unsupervised Domain Adaptation with Deep Metric Learning [arXiv 6 Jul 2018] [Pytorch(official)]
• Augmented Cyclic Adversarial Learning for Domain Adaptation [arXiv 1 Jul 2018]
• 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]
• Simple Domain Adaptation with Class Prediction Uncertainty Alignment [arXiv 12 Apr 2018]
• Causal Generative Domain Adaptation Networks [arXiv 28 Jun 2018]
• Conditional Adversarial Domain Adaptation [arXiv 10 Feb 2018 ]
• 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]
• Maximum Classifier Discrepancy for Unsupervised Domain Adaptation [CVPR2018] [Pytorch(Official)]
• Domain Generalization with Adversarial Feature Learning [CVPR2018]
• 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)]
• Incremental Adversarial Domain Adaptation for Continually Changing Environments [ICRA2018]
• A DIRT-T Approach to Unsupervised Domain Adaptation [ICLR2018 Poster] [Tensorflow(Official)]
• Label Efficient Learning of Transferable Representations acrosss Domains and Tasks [NIPS2017] [Project]
• Addressing Appearance Change in Outdoor Robotics with Adversarial Domain Adaptation [IROS2017]
• 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]

Network Methods

• Boosting Domain Adaptation by Discovering Latent Domains [CVPR2018]
• 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]
• Deep Domain Confusion: Maximizing for Domain Invariance [Arxiv 2014]

Optimal Transport

• DeepJDOT: Deep Joint distribution optimal transport for unsupervised domain adaptation [ECCV2018]
• 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

• Unsupervised Domain Adaptation with Distribution Matching Machines [AAAI2018]
• Self-Ensembling for Visual Domain Adaptation [ICLR2018 Poster]
• Minimal-Entropy Correlation Alignment for Unsupervised Deep Domain Adaptation [ICLR2018 Poster]
• Aligning Infinite-Dimensional Covariance Matrices in Reproducing Kernel Hilbert Spaces for Domain Adaptation [CVPR2018]
• Associative Domain Adaptation [ICCV2017] [TensorFlow]
• Learning Transferrable Representations for Unsupervised Domain Adaptation [NIPS2016]

Zero-shot DA

• Zero-Shot Deep Domain Adaptation [ECCV2018]

Few-shot DA

Image-to-Image Translation

• JointGAN: Multi-Domain Joint Distribution Learning with Generative Adversarial Nets [ICML2018] [TensorFlow(Official)]
• Multimodal Unsupervised Image-to-Image Translation [arXiv] [Pytorch(Official)]
• StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translation [CVPR2018][Pytorch(Official)]
• Conditional Image-to-Image Translation [CVPR2018]
• Toward Multimodal Image-to-Image Translation [NIPS2017] [Project] [Pyotorch(Official)]
• Unsupervised Image-to-Image Translation Networks [NIPS2017] [Pytorch(Official)]
• Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks [ICCV2017(extended version)][Pytorch(Official)]
• Image-to-Image Translation with Conditional Adversarial Nets [CVPR2017] [Project] [Pytorch(Official)]
• Learning to Discover Cross-Domain Relations with Generative Adversarial Networks [ICML2017] [Pytorch(Official)]
• Unsupervised Cross-Domain Image Generation [ICLR2017 Poster] [TensorFlow]
• Coupled Generative Adversarial Networks [NIPS2016] [Poytorch(Official)]

Open Set DA

• Learning Factorized Representations for Open-set Domain Adaptation [arXiv 31 May 2018]
• Open Set Domain Adaptation by Backpropagation [ECCV2018]
• Open Set Domain Adaptation [ICCV2017]

Partial DA

• Partial Adversarial Domain Adaptation [ECCV2018(not released)] [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)]

Multi source DA

• Deep Cocktail Network: Multi-source Unsupervised Domain Adaptation with Category Shift [CVPR2018]

Applications

Object Detection

• Cross-Domain Weakly-Supervised Object Detection Through Progressive Domain Adaptation [CVPR2018]
• Domain Adaptive Faster R-CNN for Object Detection in the Wild [CVPR2018]

Semantic Segmentation

• Learning From Synthetic Data: Addressing Domain Shift for Semantic Segmentation [CVPR2018]
• Curriculum Domain Adaptation for Semantic Segmentation of Urban Scenes [ICCV2017]

Person Re-identification

• Person Transfer GAN to Bridge Domain Gap for Person Re-Identification [CVPR2018]
• Image-Image Domain Adaptation with Preserved Self-Similarity and Domain-Dissimilarity for Person Re-identification [CVPR2018]

Others

• Real-Time Monocular Depth Estimation using Synthetic Data with Domain Adaptation via Image Style Transfer [CVPR2018]

Benchmarks

• Syn2Real: A New Benchmark forSynthetic-to-Real Visual Domain Adaptation [arXiv 26 Jun] [Project]