skada.deep.DeepCoral

skada.deep.DeepCoral(module, layer_name, reg=1, **kwargs)

DeepCORAL domain adaptation method.

From [12].

Parameters:

moduletorch module (class or instance)

A PyTorch Module.

layer_namestr

The name of the module's layer whose outputs are collected during the training for the adaptation.

regfloat, optional (default=1)

The regularization parameter of the covariance estimator.

References

[12]

Baochen Sun and Kate Saenko. Deep coral: Correlation alignment for deep domain adaptation. In ECCV Workshops, 2016.

Examples using skada.deep.DeepCoral

Divergence domain adaptation methods.

Divergence domain adaptation methods.

Training setup for deep DA method.

Training setup for deep DA method.