What is Feature Map? — one analogy

1The analogy

Wind turbines stand in neat rows across a hillside. On the control room screen, a grid is drawn in exactly the layout the turbines stand in, and each square shows a number for how fast that turbine is spinning right now. Where a ridge blocks the wind, the number in that row drops off; where wind comes straight through, the number climbs.

Just jotting the numbers down on a sheet of paper tells you nothing. But put them in a grid that matches where the turbines actually stand, and the line where the wind gets blocked shows up as clearly as a picture, cutting right across the hillside. What the operator does isn't reading numbers one by one — it's reading the pattern on the screen.

The screen isn't just one, either. Keep a dawn screen, a midday screen, a windy-day screen, and you end up with several layers stacked over the same hillside. Feature maps stack up the same way — several of them, each still holding its position.

2In detail

Holding a position is the whole point

The key to understanding a feature map isn't "what is the value" — it's "where is the value." Scanning produces one score per spot on the photo, and if those scores get dumped into a sack with no regard for where they came from, they're useless. Laying each score onto a grid at exactly the spot it came from is what turns it into a picture.

That's why a feature map ends up similar in shape to the original photo. Its width and height shift a little depending on the scan width and edge handling, but the top left is still the top left and the bottom right is still the bottom right. If an object sat on the right side of the photo, the spots with big values cluster on the right side of the feature map too.

This property is exactly what makes it possible to figure out where an object is. Whether it's putting a single label on a photo, boxing every object, or cutting things out pixel by pixel, all of it works by tracing back the position that's kept intact in a feature map.

It's a bundle, not a single sheet

A layer holds anywhere from dozens to hundreds of tiles, and since each one scans separately, you get that many results — a picture from the tile hunting for vertical lines, a picture from the tile hunting for a sudden color change, stacked up side by side.

Looking at the same spot across several of these pictures at once tells you something about that spot's character. A spot that's high in both the vertical-line picture and the horizontal-line picture is likely where two lines meet — a corner. The next layer uses exactly this: scanning with a thick tile that spans all the pictures at once, it looks at which pictures are lit up together and recognizes bigger parts from that.

It gets smaller and thicker going up

Every layer it passes through, a feature map's shape changes in a predictable way. Pooling or a bigger stride halves the width and height; adding more tiles doubles the count. What starts wide and thin ends up small and thick.

What this shift means is clear enough. One square in an early feature map points to a fingernail-sized spot on the original photo, but one square in a later feature map summarizes a whole wide region of the photo at once. Position gets blurred, and in its place sits the meaning of "what was around here." By the last layer, only a few squares remain in width and height, and one square all but stands in for the entire photo.

Only the early ones are recognizable by eye

Pull a feature map out and look at it as a picture, and the first layer is easy to make sense of — an outline-only photo, a photo where lines running one direction stand out — the traces of the original are still there. You can more or less guess what it caught, just by eye.

Further back, things change. It looks like a blotchy small grid, and it's not obvious at a glance why any particular square lit up, because it's dealing with patterns that don't have a name a person would give them. That's why people trying to see what a model based its judgment on don't look at the raw feature map — instead they overlay, in color, which spots contributed most to the conclusion, right on top of the original photo.

3More precisely

A feature map is the output of a convolution layer. It's a block of values with three directions — width, height, and count — where the count matches the number of filters in that layer. Each value is the number left after adding a reference value to a sum of products and passing it through an activation function. Because it's common to use an activation function that pushes negative values down to zero, a real feature map has a lot of squares sitting at exactly zero.

The control-room analogy breaks down in one place. A number on the screen comes from one turbine, but a single square in a feature map isn't the result of one point on the original photo — it's the joint result of that point and the points around it. The deeper the layer, the wider the range of the original photo one square ends up covering, until a late square corresponds to a large chunk of the photo.

And a control screen is built for a person to read, but a feature map is a mid-way result built for the next layer to use. It can be drawn out as a picture, but it isn't laid out for a person to read comfortably.

4Try it yourself

CNN Explainer ailearn.space Click through the layers to see exactly how many pictures come out of each one and what they look like

5Common misconceptions

It's easy to think a feature map is a blurred version of the original photo, but actually it isn't a photo at all — it's a table of scores laid out spot by spot.
It's easy to assume one feature map holds one object, but actually a single one is just the response to one pattern, and an object shows up scattered across several of them.
It's easy to think the number of pictures stays the same across layers, but actually the tile count differs from layer to layer, so the picture count shifts right along with it.

7One-line summary

In shortA feature map is a picture that lays the scores a scan gave, spot by spot, out in their original arrangement, and climbing the layers it gets smaller and thicker as it trades position for meaning.

Did this analogy help?

Spotted an error or have a better analogy? Suggest an edit · Last updated2026-09-02