Grad-CAM

ˈgrædˌkæm

Gradient-weighted Class Activation Mapping (Grad-CAM) is a visualization technique used to interpret the decisions made by convolutional neural networks (CNNs). It highlights the regions of an input image that are most influential in the model's prediction, providing insights into the model's focus areas. Grad-CAM works by using the gradients of the target class flowing into the final convolutional layer to produce a coarse localization map. This technique is particularly useful in applications such as image classification and object detection, where understanding model behavior is crucial for trust and transparency.