L2-CAF: A Neural Network Debugger

Figure 1: We debug our code using a debugger (e.g., gdb). The debugger helps us execute a few instructions between two points in our programs (S1 and S2).
Figure 2: L2-CAF debugs a CNN. L2-CAF helps us understand the CNN by both monitoring its execution between two points (S1 and S2) and identifying the key features between these two points.
Figure 3: L2-CAF solves this constraint optimization problem to visualize attention in CNNs. L2-CAF is a tiny debugger network that debugs CNNs.
Figure 4: L2-CAF multiplies the convolutional feature maps by the filter f using Hadamard (element-wise) multiplication. (Top) The filter f is all ones, the objective function equals zero but the L2-Norm constraint is violated. (Bottom) The filter highlights a key feature inside the feature maps; accordingly, the objective function is minimum while the L2-Norm constraint is satisfied.
Figure 5: L2-CAF supports other constraints. Yet, the L2-Norm constraint is the best. A softmax constraint offers a sparse result while the Gaussian filter assumes a single mode. L2-CAF supports multi-modes.
Figure 6: L2-CAF comes in two flavors: class-oblivious and class-specific. This separates L2-CAF from dominant literature that targets classification networks only.
Figure 7: L2-CAF visualizes attention in both the last and intermediate convolutional layers.
I will just leave this here https://electrical-engineering-portal.com/measuring-resistance-voltage-current-digital-multimeter



Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store
Ahmed Taha

Ahmed Taha

I write reviews on computer vision papers. Writing tips are welcomed.