Spatial-Channel Attention-Based Class Activation Mapping for Interpreting CNN-Based Image Classification Models

<div>Visualizations of CAWs of ResNet-18. (a) ResNet-18: softmax weight (CAW) of the top three classes. (b) ResNet-18: average gradient (CAW) of the top three classes.</div>

Security and Communication Networks

fig11

Figure 11

Figure 11: Spatial-Channel Attention-Based Class Activation Mapping for Interpreting CNN-Based Image Classification Models 