Feature maps (Activation maps)

From Computer Science Wiki

Exclamation.png This is student work which has not yet been approved as correct by the instructor

Case study notes[1]


The feature map is the output of one filter applied to the previous layer. A given filter is drawn across the entire previous layer, moved one pixel at a time. Each position results in an activation of the neuron and the output is collected in the feature map. You can see that if the receptive field is moved one pixel from activation to activation, then the field will overlap with the previous activation by (field width - 1) input values.

 <ref> https://www.quora.com/What-is-meant-by-feature-maps-in-convolutional-neural-networks </ref>

How does it work or a deeper look[edit]

Convolutional Neural Networks look for "features" such as straight lines, or cats. As such whenever you spot those features-they get reported to the feature map. Each feature map is looking for something else. One feature map could be looking for straight lines, the other for curves. The feature maps also look for their features in different locations.


For instance, In a 32 × 32 image , dragging the 5 × 5 receptive field across the input image data with a stride width of 1 will result in a feature map of 28 × 28 (32–5+1 × 32–5+1) output values or 784 distinct activations per image. Basically this feature map shows how many times a neuron is fired off-or how many different receptive fields will be formed

Pictures, diagrams[edit]

Pictures and diagrams go a LONG way to helping someone understand a topic. Especially if your topic is a little abstract or complex. Using a picture or diagram is a two part process:

  1. upload a file
  2. use the file on a wiki page

External links[edit]

  • It would be helpful
  • to include many links
  • to other internet resources
  • to help fellow students
  • Please make sure the content is good
  • and don't link to a google search results, please