• Welcome to DomainAdaptation
• • Available algorithms
  • Available datasets

Welcome to DomainAdaptation

This project is an PyTorch suite containing benchmark datasets and algorithms for domain adaptation.
The codes have referred from the DomainBed.

Available algorithms

The currently available algorithms and the corresponding papers are described as follows:

• Empirical Risk Minimization (ERM, Vapnik, 1998)

• Invariant Risk Minimization (IRM, Arjovsky et al., 2019)

• Group Distributionally Robust Optimization (GroupDRO, Sagawa et al., 2020)

• Interdomain Mixup (Mixup, Yan et al., 2020)

• Marginal Transfer Learning (MTL, Blanchard et al., 2011-2020)

• Meta Learning Domain Generalization (MLDG, Li et al., 2017)

• Maximum Mean Discrepancy (MMD, Li et al., 2018)

• Deep CORAL (CORAL, Sun and Saenko, 2016)

• Domain Adversarial Neural Network (DANN, Ganin et al., 2015)

• Conditional Domain Adversarial Neural Network (CDANN, Li et al., 2018)

• Style Agnostic Networks (SagNet, Nam et al., 2020)

• Adaptive Risk Minimization (ARM, Zhang et al., 2020), contributed by @zhangmarvin

• Variance Risk Extrapolation (VREx, Krueger et al., 2020), contributed by @zdhNarsil

• Representation Self-Challenging (RSC, Huang et al., 2020), contributed by @SirRob1997

• Spectral Decoupling (SD, Pezeshki et al., 2020)

• Learning Explanations that are Hard to Vary (AND-Mask, Parascandolo et al., 2020)

• Out-of-Distribution Generalization with Maximal Invariant Predictor (IGA, Koyama et al., 2020)

• Gradient Matching for Domain Generalization (Fish, Shi et al., 2021)

• Self-supervised Contrastive Regularization (SelfReg, Kim et al., 2021)

• Smoothed-AND mask (SAND-mask, Shahtalebi et al., 2021)

• Learning Representations that Support Robust Transfer of Predictors (TRM, Xu et al., 2021)

• Invariance Principle Meets Information Bottleneck for Out-of-Distribution Generalization (IB-ERM , Ahuja et al., 2021)

• Invariance Principle Meets Information Bottleneck for Out-of-Distribution Generalization (IB-IRM, Ahuja et al., 2021)

• Optimal Representations for Covariate Shift (CAD & CondCAD, Ruan et al., 2022), contributed by @ryoungj

• Invariant Causal Mechanisms through Distribution Matching (CausIRL with CORAL or MMD, Chevalley et al., 2022), contributed by @MathieuChevalley

• ADBlur enforced Vision Transformer (ViT), Swin Transformer, ERM, IRM, GroupDRO, Mixup, MLDG, MMD, MTL, SagNet, CORAL, ARM are our work undering review by the AAAI 2023.

Available datasets

The currently available datasets are:

• camelyon17_v1.0 (Pinchaud N et al. 2019)
• DomainNet (Peng et al., 2019)
• fMoW ( Christie et al., 2018)
• RotatedMNIST (Ghifary et al., 2015)
• ColoredMNIST (Arjovsky et al., 2019)
• Office31 (Saenko et al. 2010)
• VLCS (Fang et al., 2013)
• PACS (Li et al., 2017)
• Office-Home (Venkateswara et al., 2017)
• TerraIncognita (Beery et al., 2018)
• WILDS (Koh et al., 2020)

Train a model:

python train.py --data_dir=data/MNIST/ --algorithm ADBlur --dataset RotatedMNIST --test_env 2