Paper Link: Model Adaptation: Unsupervised Domain Adaptation Without Source Data (thecvf.com)

Key Elements

1. Target Generation:

   • Collaborative Class Conditional GAN (3CGAN)

     • Domain Discriminator D:

       $ \max_{\theta_D} \mathbb E_{x_t \sim D_t } [log D(x_t)] + \mathbb E_{y,z}[log(1-D(G(y,z)))]$

       Which is try to tell whether its inputs are original target samples or generated target sample

     • Generator G:

       $l_{adv}(G)=\mathbb E_{y,z}[logD(1-G(y,z))]$ $\min_{\theta_G}l_{adv}+\lambda_sl_{sem}$

       Which is trying to confuse the Domain Discriminator D

       And minimize the cross-entropy loss

     • Fixed Predictor C (Pretrained on source domain):

       $l_{sem}(G)=\mathbb E_{y,z}[-ylog_{p_{\theta_C}}(G(y,z))]$

       Which is there to check whether the generated samples... read more

Paper Link: AutoDIAL: Automatic DomaIn Alignment Layers (thecvf.com)

Supplementary Material: Carlucci_AutoDIAL_Automatic_DomaIn_ICCV_2017_supplemental.pdf (thecvf.com)

Code Link: https://github.com/ducksoup/autodial

Key Elements

• Softmax loss on source samples
• Entropy minimizaiton on target samples
• DA-layers to adapt the features

DA Layer

• The DA layer used for source data and the DA layer used for target data is probably going to be different, because there is a large probability that the distributions of source and target are different.

• Every DA layer will have an $\alpha$ parameter, used for determining how deeply the DA layer will adapt to its input data.

• ... read more

Paper Link: https://arxiv.org/pdf/1612.01939.pdf

Code Link: https://github.com/VisionLearningGroup/CORAL

What Had the Authors Proposed

1. CORrelation ALignment (CORAL): minimizes domain shift by aligning the second-order statistics of source and target distributions
2. A solution that applies a linear transformation to source features to align them with target features before classifier training
3. How to apply CORAL to classifier weights
4. How to apply CORAL to deep neural networks

The Steps of the Linear Transformation

1. Normalize the source and target features to zero mean and unit variance
2. Remove the feature correlations of the source domain, which can be seen as the procedure of “de-coloring” the... read more