U-Net
U-Net finds exact shapes in an image by shrinking the image down and then building a detailed map back up.
What it does
U-Net finds exact shapes in an image by shrinking the image down and then building a detailed map back up.
Segmentation: Coloring specific pixels • Architecture: Brain shape
How it works
- Shrink the image to understand the big picture.
- Grow it back to the original size.
- Mark which pixels belong to the object.
Uses & Applications
- A medical tool can outline organs or tumors for a doctor to inspect.
- A map tool can outline roads or buildings in satellite images.
- A photo editor can separate a person from the background.
In short
U-Net is useful for pixel-level image masks.
Try it yourself
Find the shape inside a noisy picture
Shrink a picture to see its broad shape. Then grow the view again and add fine details to decide which squares belong to the shape.
Your turn
Change one setting at a time. Reset example puts everything back.
Shrink context, restore pixel location
Step 1Why this happens