PerturbationOcclusion

class xaitk_saliency.impls.gen_image_classifier_blackbox_sal.occlusion_based.PerturbationOcclusion(*, perturber: PerturbImage, generator: GenerateClassifierConfidenceSaliency, threads: int = 0)

Generator composed of modular perturbation and occlusion-based algorithms.

This implementation exposes a public attribute fill. This may be set to a scalar or sequence value to indicate a color that should be used for filling occluded areas as determined by the given PerturbImage implementation. This is a parameter to be set during runtime as this is most often driven by the black-box algorithm used, if at all.

Example:

>>> from xaitk_saliency._fakes import FakeClassifyImage
>>> from xaitk_saliency.impls.gen_classifier_conf_sal.occlusion_scoring import OcclusionScoring
>>> from xaitk_saliency.impls.perturb_image.sliding_window import SlidingWindow
>>> n_classes, height, width = 1, 18, 24
>>> ref_image = np.zeros((height, width, 3), dtype=np.uint8)
>>> gen = PerturbationOcclusion(
...     perturber=SlidingWindow(window_size=(8, 8), stride=(8, 8)),
...     generator=OcclusionScoring(),
... )
>>> sal = gen.generate(ref_image=ref_image, blackbox=FakeClassifyImage({0: 1.0}))
>>> sal.shape == (n_classes, height, width)
True

Methods

from_config	Create a PerturbationOcclusion instance from a configuration dictionary.
generate	Generates per-class visual saliency heatmaps for some classifier black box over some image of interest.
get_config	Get the configuration dictionary of the PerturbationOcclusion instance.
get_default_config	Returns the default configuration for the PerturbationOcclusion.
get_impls	Discover and return a set of classes that implement the calling class.
is_usable	Check whether this class is available for use.

__init__(*, perturber: PerturbImage, generator: GenerateClassifierConfidenceSaliency, threads: int = 0) → None

Initialization of a generator for modular perturbation and occlusion-based algorithms.

Parameters:

• perturber – PerturbImage implementation instance for generating masks that will dictate occlusion.

• generator – Implementation instance for generating saliency masks given occlusion masks and classifier outputs.

• threads – Optional number threads to use to enable parallelism in applying perturbation masks to an input image. If 0, a negative value, or None, work will be performed on the main-thread in-line.

classmethod from_config(config_dict: dict[str, Any], merge_default: bool = True) → Self

Create a PerturbationOcclusion instance from a configuration dictionary.

Args:

config_dict (dict): Configuration dictionary with perturber details. merge_default (bool): Whether to merge with the default configuration.

Returns:

PerturbationOcclusion: An instance of PerturbationOcclusion.

get_config() → dict[str, Any]

Get the configuration dictionary of the PerturbationOcclusion instance.

Returns:

dict[str, Any]: Configuration dictionary.

classmethod get_default_config() → dict[str, Any]

Returns the default configuration for the PerturbationOcclusion.

This method provides a default configuration dictionary, specifying default values for key parameters in the factory. It can be used to create an instance of the factory with preset configurations.

Returns:

dict[str, Any]: A dictionary containing default configuration parameters.