Skip to main content
Advertisement
Browse Subject Areas
?

Click through the PLOS taxonomy to find articles in your field.

For more information about PLOS Subject Areas, click here.

< Back to Article

Fig 1.

An illustration of unsupervised multi-source domain adaptation (UMDA) problems.

(a) illustrates UMDA problem with observable source data, and (b) illustrates data-free UMDA problem with no observable source data. It is challenging to reduce the distribution discrepancy between source and target domains in (b) since there are no accessible source data.

More »

Fig 1 Expand

Table 1.

Comparison of DEMS and other methods.

More »

Table 1 Expand

Table 2.

Table of frequently-used symbols.

More »

Table 2 Expand

Fig 2.

Classification accuracy.

DEMS shows the best classification accuracy for five target domains; each percentage indicates the accuracy increase compared to the second-best one for each target domain.

More »

Fig 2 Expand

Table 3.

Comparison of different latent space transformation methods for unsupervised multi-source domain adaptation (UMDA).

More »

Table 3 Expand

Fig 3.

Overall architecture of DEMS.

More »

Fig 3 Expand

Table 4.

Summary of datasets.

More »

Table 4 Expand

Fig 4.

Sample images (10 classes).

More »

Fig 4 Expand

Table 5.

Classification accuracy of DEMS and baselines.

More »

Table 5 Expand

Table 6.

Ablation study on MNIST-M target dataset.

More »

Table 6 Expand

Fig 5.

Visualization of image adaptation from MNIST-M to other source domains.

Fig (a) enumerates target samples for Figs (b), (c), (d), and (e). The target samples are adapted by adaptation networks which are trained with different losses. For DEMS (Fig (b)), the adaptation gradually focuses on the close source domains (MNIST, SVHN, and SynDigits), resulting in performance enhancement. For (Fig (c)), some classes (digits 3, 7, and 9) are failed to be adapted to source domains. For and (Figs (d) and (e)), the adaptations are not trained at all.

More »

Fig 5 Expand

Fig 6.

Sensitivity of accuracy to the hyperparameters ϵ (Eq 10) and λ (Eqs 2 and 6).

More »

Fig 6 Expand