occlusionSensitivity
Explain network predictions by occluding the inputs
Description
computes a map of the change in total activation for the specified channel when parts of the
input data scoreMap
= occlusionSensitivity(net
,X
,channelIdx
)X
are occluded with a mask. The change in score is relative to
the original data without occlusion. The occluding mask is moved across the input data,
giving a change in score for each mask location. Use an occlusion sensitivity map to
identify the parts of your input data that most impact the score. Areas in the map with
higher positive values correspond to regions of input data that contribute positively to the
specified channel index. For classification tasks, specify the
channelIdx
as the channel in the softmax layer corresponding to the
class label of interest.
___ = occlusionSensitivity(___,
specifies options using one or more name-value arguments in addition to the input arguments
in previous syntaxes. For example, Name=Value
)Stride=50
sets the stride of the
occluding mask to 50 pixels.
Examples
Input Arguments
Name-Value Arguments
Output Arguments
Extended Capabilities
Version History
Introduced in R2019bSee Also
dlnetwork
| testnet
| minibatchpredict
| scores2label
| imageLIME
| gradCAM
| predict
| forward
Topics
- Understand Network Predictions Using Occlusion
- Grad-CAM Reveals the Why Behind Deep Learning Decisions
- Understand Network Predictions Using LIME
- Investigate Network Predictions Using Class Activation Mapping
- Visualize Features of a Convolutional Neural Network
- Visualize Activations of a Convolutional Neural Network