Visualizing CNN Feature Maps Flashcards

What does a feature map (activation map) represent in a CNN layer?

Answer: The output of applying a learned filter across the input

A feature map is produced by convolving a learned filter over the input, showing where and how strongly that filter's pattern is detected.

When visualizing early-layer feature maps, what kind of patterns are typically detected?

Answer: Low-level patterns like edges, colors, and textures

Early CNN layers respond to simple, low-level visual features such as oriented edges, color gradients, and basic textures.

Which Python library function is commonly used to extract intermediate layer outputs for feature map visualization in Keras?

Answer: Model(inputs, intermediate_layer.output)

Creating a new Keras Model with the original input and an intermediate layer's output allows you to forward-pass an image and retrieve that layer's activations.

If a feature map appears mostly dark (near-zero activations), what does this indicate?

Answer: The filter's learned pattern is not present in the input region

Near-zero activations mean the convolutional filter did not detect its corresponding pattern in those spatial locations of the input.

What is the spatial dimension relationship between an input feature map and output feature map when using a 3×3 filter with padding='same' and stride=1?

Answer: Output is the same spatial size as the input

With 'same' padding and stride=1, zero-padding is added so the output spatial dimensions exactly match the input dimensions.

In a CNN with 64 filters in a convolutional layer, how many feature maps does that layer produce per input image?

Answer: 64

Each filter produces exactly one feature map, so 64 filters yield 64 feature maps per input sample.

What visualization technique overlays a heatmap on the input image to show which regions most influenced a CNN's prediction?

Answer: Grad-CAM (Gradient-weighted Class Activation Mapping)

Grad-CAM uses the gradients of the target class flowing into the final convolutional layer to produce a localization heatmap.