IS-CAM: Integrated Score-CAM for axiomatic-based explanations
This work addresses the need for more interpretable and trustworthy CNNs, though it appears incremental as it builds on the existing Score-CAM method.
The authors tackled the problem of interpreting Convolutional Neural Networks (CNNs) as black-box models by proposing IS-CAM (Integrated Score-CAM), which integrates operations into the Score-CAM pipeline to produce sharper attribution maps, as demonstrated on 2000 images from the ILSVRC 2012 dataset.
Convolutional Neural Networks have been known as black-box models as humans cannot interpret their inner functionalities. With an attempt to make CNNs more interpretable and trustworthy, we propose IS-CAM (Integrated Score-CAM), where we introduce the integration operation within the Score-CAM pipeline to achieve visually sharper attribution maps quantitatively. Our method is evaluated on 2000 randomly selected images from the ILSVRC 2012 Validation dataset, which proves the versatility of IS-CAM to account for different models and methods.